| Qwen3.6-35B-A3B-NVFP4 | nvfp4 | nvfp4 | | 9,864,413 | Qwen/Qwen3.6-35B-A3B |
| NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4 | nvfp4 | nvfp4 | 812.7 | 3,017,149 | nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16 |
| Gemma-4-31B-IT-NVFP4 | nvfp4 | nvfp4 | | 2,707,994 | google/gemma-4-31B-it |
| Qwen3.6-27B-NVFP4 | nvfp4 | nvfp4 | | 1,915,154 | Qwen/Qwen3.6-27B |
| diffusiongemma-26B-A4B-it-NVFP4 | nvfp4 | nvfp4 | | 1,736,406 | google/diffusiongemma-26B-A4B-it |
| parakeet-ctc-1.1b | original | bf16 | 1,024 | 1,632,235 | nvidia/parakeet-ctc-1.1b |
| GLM-5.2-NVFP4 | nvfp4 | nvfp4 | | 1,607,192 | zai-org/GLM-5.2 |
| bigvgan_v2_22khz_80band_256x | original | bf16 | | 1,556,442 | nvidia/bigvgan_v2_22khz_80band_256x |
| Nemotron-3-Nano-Omni-30B-A3B-Reasoning-NVFP4 | nvfp4 | nvfp4 | | 1,548,544 | nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16 |
| NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4 | nvfp4 | nvfp4 | 812.7 | 1,370,051 | nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 |
| DeepSeek-V4-Flash-NVFP4 | nvfp4 | nvfp4 | | 1,341,250 | deepseek-ai/DeepSeek-V4-Flash |
| Llama-3.1-Nemotron-Nano-VL-8B-V1 | original | bf16 | | 1,269,297 | nvidia/Llama-3.1-Nemotron-Nano-VL-8B-V1 |
| LocateAnything-3B | original | bf16 | | 1,249,399 | Qwen/Qwen2.5-3B-Instruct |
| Gemma-4-26B-A4B-NVFP4 | nvfp4 | nvfp4 | | 1,185,207 | google/gemma-4-26B-A4B-it |
| llama-nemotron-rerank-1b-v2 | original | bf16 | | 1,073,153 | nvidia/llama-nemotron-rerank-1b-v2 |
| nemotron-3.5-asr-streaming-0.6b | original | bf16 | | 1,014,552 | nvidia/nemotron-3.5-asr-streaming-0.6b |
| mit-b2 | original | bf16 | | 1,002,539 | nvidia/mit-b2 |
| bigvgan_v2_44khz_128band_512x | original | bf16 | | 976,500 | nvidia/bigvgan_v2_44khz_128band_512x |
| NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 | original | bf16 | 812.7 | 965,237 | nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 |
| NVIDIA-Nemotron-3-Super-120B-A12B-BF16 | original | bf16 | 812.7 | 889,424 | nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16 |
| Nemotron-3-Nano-Omni-30B-A3B-Reasoning-FP8 | fp8 | fp8 | | 868,610 | nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16 |
| llama-nemotron-embed-1b-v2 | original | bf16 | | 826,975 | nvidia/llama-nemotron-embed-1b-v2 |
| parakeet-tdt-0.6b-v2 | original | bf16 | | 763,375 | nvidia/parakeet-tdt-0.6b-v2 |
| NVIDIA-Nemotron-3-Nano-4B-BF16 | original | bf16 | 997.3 | 702,820 | nvidia/NVIDIA-Nemotron-Nano-9B-v2 |
| Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16 | original | bf16 | | 639,016 | nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16 |
| Kimi-K2.6-NVFP4 | nvfp4 | nvfp4 | | 625,624 | moonshotai/Kimi-K2.6 |
| MiniMax-M3-NVFP4 | nvfp4 | nvfp4 | | 556,436 | MiniMaxAI/MiniMax-M3 |
| NVIDIA-Nemotron-3-Nano-30B-A3B-FP8 | fp8 | fp8 | 812.7 | 531,253 | nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 |
| Cosmos-Reason2-2B | original | bf16 | | 446,147 | Qwen/Qwen3-VL-2B-Instruct |
| Kimi-K2.7-Code-NVFP4 | nvfp4 | nvfp4 | | 436,839 | moonshotai/Kimi-K2.7-Code |
| Nemotron-Labs-Diffusion-8B-Base | original | bf16 | | 430,108 | nvidia/Nemotron-Labs-Diffusion-8B-Base |
| Phi-4-reasoning-plus-NVFP4 | nvfp4 | nvfp4 | | 395,307 | microsoft/Phi-4-reasoning-plus |
| segformer-b0-finetuned-ade-512-512 | original | bf16 | | 385,366 | nvidia/segformer-b0-finetuned-ade-512-512 |
| NVIDIA-Nemotron-Nano-12B-v2 | original | bf16 | 997.3 | 383,905 | nvidia/NVIDIA-Nemotron-Nano-12B-v2-Base |
| DeepSeek-R1-0528-NVFP4-v2 | nvfp4 | nvfp4 | | 383,321 | deepseek-ai/DeepSeek-R1-0528 |
| Kimi-K2.5-NVFP4 | nvfp4 | nvfp4 | | 368,708 | moonshotai/Kimi-K2.5 |
| NVIDIA-Nemotron-Parse-v1.1 | original | bf16 | | 367,197 | nvidia/NVIDIA-Nemotron-Parse-v1.1 |
| Qwen3.5-397B-A17B-NVFP4 | nvfp4 | nvfp4 | | 350,252 | Qwen/Qwen3.5-397B-A17B |
| Nemotron-3-Embed-1B-BF16 | original | bf16 | | 338,815 | mistralai/Ministral-3-3B-Instruct-2512 |
| Qwen3-VL-235B-A22B-Instruct-NVFP4-MLPerf-Inference-Closed-V6.1-FP8-KV | nvfp4 | nvfp4 | | 335,330 | Qwen/Qwen3-VL-235B-A22B-Instruct |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 | original | bf16 | 860 | 328,914 | nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 |
| Llama-4-Scout-17B-16E-Instruct-FP8 | fp8 | fp8 | | 323,245 | meta-llama/Llama-4-Scout-17B-16E-Instruct |
| Cosmos3-Nano | original | bf16 | | 305,407 | nvidia/Cosmos3-Nano |
| NVIDIA-Nemotron-Nano-9B-v2 | original | bf16 | | 297,784 | nvidia/NVIDIA-Nemotron-Nano-12B-v2-Base |
| segformer-b2-finetuned-ade-512-512 | original | bf16 | | 284,864 | nvidia/segformer-b2-finetuned-ade-512-512 |
| KVzap-mlp-Qwen3-8B | original | bf16 | | 282,569 | nvidia/KVzap-mlp-Qwen3-8B |
| Cosmos-Reason2-8B | original | bf16 | | 272,459 | Qwen/Qwen3-VL-8B-Instruct |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4 | nvfp4 | nvfp4 | | 260,898 | nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 |
| Qwen3.5-122B-A10B-NVFP4 | nvfp4 | nvfp4 | | 259,262 | Qwen/Qwen3.5-122B-A10B |
| Llama-3_3-Nemotron-Super-49B-v1_5-FP8 | fp8 | fp8 | | 254,929 | nvidia/Llama-3_3-Nemotron-Super-49B-v1_5 |
| personaplex-7b-v1 | original | bf16 | | 247,706 | kyutai/moshiko-pytorch-bf16 |
| Nemotron-Mini-4B-Instruct | original | bf16 | | 247,494 | nvidia/Nemotron-Mini-4B-Instruct |
| NVIDIA-Nemotron-Parse-v1.2 | original | bf16 | | 231,083 | nvidia/NVIDIA-Nemotron-Parse-v1.2 |
| Phi-4-multimodal-instruct-NVFP4 | nvfp4 | nvfp4 | | 224,215 | microsoft/Phi-4-multimodal-instruct |
| NVIDIA-Nemotron-3-Super-120B-A12B-FP8 | fp8 | fp8 | | 223,554 | nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16 |
| parakeet-tdt-0.6b-v3 | original | bf16 | | 202,172 | nvidia/parakeet-tdt-0.6b-v3 |
| Llama-3.1-8B-Instruct-NVFP4 | nvfp4 | nvfp4 | | 201,445 | meta-llama/Llama-3.1-8B-Instruct |
| NVIDIA-Nemotron-Nano-12B-v2-VL-NVFP4-QAD | nvfp4 | nvfp4 | | 198,946 | nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16 |
| audio-flamingo-3-hf | original | bf16 | | 197,695 | nvidia/audio-flamingo-3-hf |
| Nemotron-Labs-Diffusion-8B | original | bf16 | | 183,623 | nvidia/Nemotron-Labs-Diffusion-8B |
| Llama-3_3-Nemotron-Super-49B-v1 | original | bf16 | | 181,588 | nvidia/Llama-3_3-Nemotron-Super-49B-v1 |
| NVLM-D-72B | original | bf16 | | 178,174 | nvidia/NVLM-D-72B |
| NVIDIA-Nemotron-Nano-12B-v2-VL-BF16 | original | bf16 | | 176,843 | nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16 |
| nemotron-speech-streaming-en-0.6b | original | bf16 | | 164,013 | nvidia/nemotron-speech-streaming-en-0.6b |
| Qwen3-8B-NVFP4 | nvfp4 | nvfp4 | | 159,182 | Qwen/Qwen3-8B |
| Qwen3-235B-A22B-NVFP4 | nvfp4 | nvfp4 | | 157,931 | Qwen/Qwen3-235B-A22B |
| Nemotron-Labs-Diffusion-3B-Base | original | bf16 | | 141,903 | nvidia/Nemotron-Labs-Diffusion-3B-Base |
| GLM-5-NVFP4 | nvfp4 | nvfp4 | | 135,825 | zai-org/GLM-5 |
| Cosmos-Predict2-2B-Video2World | original | bf16 | | 129,652 | nvidia/Cosmos-Predict2-2B-Video2World |
| Eagle2.5-8B | merge | merge | | 129,409 | Qwen/Qwen2.5-7B-Instruct |
| NVIDIA-Nemotron-Nano-9B-v2-FP8 | fp8 | fp8 | | 128,501 | nvidia/NVIDIA-Nemotron-Nano-9B-v2 |
| Qwen3-14B-NVFP4 | nvfp4 | nvfp4 | | 123,890 | Qwen/Qwen3-14B |
| llama-nemotron-rerank-vl-1b-v2 | original | bf16 | | 120,135 | nvidia/llama-nemotron-rerank-vl-1b-v2 |
| Cosmos3-Super | original | bf16 | | 102,474 | nvidia/Cosmos3-Super |
| llama-nemotron-embed-vl-1b-v2 | original | bf16 | | 101,225 | nvidia/llama-nemotron-embed-vl-1b-v2 |
| DeepSeek-V4-Pro-NVFP4 | nvfp4 | nvfp4 | | 100,545 | deepseek-ai/DeepSeek-V4-Pro |
| Nemotron-3-Embed-8B-BF16 | original | bf16 | | 100,422 | mistralai/Ministral-3-8B-Instruct-2512 |
| speakerverification_en_titanet_large | original | bf16 | | 98,657 | nvidia/speakerverification_en_titanet_large |
| segformer-b1-finetuned-ade-512-512 | original | bf16 | | 97,347 | nvidia/segformer-b1-finetuned-ade-512-512 |
| Llama-3.3-70B-Instruct-FP8 | fp8 | fp8 | | 95,548 | meta-llama/Llama-3.3-70B-Instruct |
| NVIDIA-Nemotron-3-Nano-4B-FP8 | fp8 | fp8 | | 91,506 | nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16 |
| diar_streaming_sortformer_4spk-v2.1 | original | bf16 | | 88,660 | nvidia/diar_streaming_sortformer_4spk-v2.1 |
| Nemotron-Labs-Diffusion-3B | original | bf16 | | 87,931 | nvidia/Nemotron-Labs-Diffusion-3B |
| Nemotron-H-8B-Base-8K | original | bf16 | | 86,116 | nvidia/Nemotron-H-8B-Base-8K |
| Nemotron-Cascade-2-30B-A3B | original | bf16 | | 82,501 | nvidia/Nemotron-Cascade-2-30B-A3B |
| music-flamingo-2601-hf | original | bf16 | | 81,963 | nvidia/music-flamingo-2601-hf |
| Llama-3.3-70B-Instruct-NVFP4 | nvfp4 | nvfp4 | | 81,769 | meta-llama/Llama-3.3-70B-Instruct |
| mit-b0 | original | bf16 | | 79,020 | nvidia/mit-b0 |
| Qwen3-14B-FP8 | fp8 | fp8 | | 74,381 | Qwen/Qwen3-14B |
| MiniMax-M2.7-NVFP4 | nvfp4 | nvfp4 | | 73,704 | MiniMaxAI/MiniMax-M2.7 |
| Llama-3.1-8B-Instruct-FP8 | fp8 | fp8 | | 73,625 | meta-llama/Llama-3.1-8B-Instruct |
| Llama-4-Scout-17B-16E-Instruct-NVFP4 | nvfp4 | nvfp4 | | 72,603 | meta-llama/Llama-4-Scout-17B-16E-Instruct |
| NVIDIA-Nemotron-3-Nano-30B-A3B-Base-BF16 | original | bf16 | | 72,272 | nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-Base-BF16 |
| Qwen3-32B-NVFP4 | nvfp4 | nvfp4 | | 70,912 | Qwen/Qwen3-32B |
| NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-NVFP4 | nvfp4 | nvfp4 | | 64,317 | nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16 |
| Qwen3-30B-A3B-NVFP4 | nvfp4 | nvfp4 | | 62,746 | Qwen/Qwen3-30B-A3B |
| Llama-3_3-Nemotron-Super-49B-v1_5 | original | bf16 | | 57,679 | nvidia/Llama-3_3-Nemotron-Super-49B-v1_5 |
| llama-embed-nemotron-8b | original | bf16 | | 56,182 | nvidia/llama-embed-nemotron-8b |
| NV-Generate-CT | original | bf16 | | 54,435 | nvidia/NV-Generate-CT |
| DeepSeek-V3.1-NVFP4 | nvfp4 | nvfp4 | | 52,591 | deepseek-ai/DeepSeek-V3.1 |
| Llama-3.1-Nemotron-Nano-8B-v1 | original | bf16 | | 52,529 | nvidia/Llama-3.1-Nemotron-Nano-8B-v1 |
| canary-1b-v2 | original | bf16 | | 50,940 | nvidia/canary-1b-v2 |
| canary-qwen-2.5b | original | bf16 | | 49,755 | nvidia/canary-1b-flash |
| segformer-b5-finetuned-ade-640-640 | original | bf16 | | 49,686 | nvidia/segformer-b5-finetuned-ade-640-640 |
| Alpamayo-1.5-10B | original | bf16 | | 48,589 | nvidia/Cosmos-Reason2-8B |
| GR00T-N1.7-3B | original | bf16 | | 44,108 | nvidia/GR00T-N1.7-3B |
| diar_streaming_sortformer_4spk-v2 | original | bf16 | | 43,723 | nvidia/diar_streaming_sortformer_4spk-v2 |
| gpt-oss-puzzle-88B | torchao | torchao | | 40,120 | — |
| Qwen3-Next-80B-A3B-Instruct-NVFP4 | nvfp4 | nvfp4 | | 39,585 | Qwen/Qwen3-Next-80B-A3B-Instruct |
| Llama-3.1-Nemotron-70B-Instruct-HF | original | bf16 | | 39,363 | meta-llama/Llama-3.1-70B-Instruct |
| parakeet-rnnt-0.6b | original | bf16 | | 38,179 | nvidia/parakeet-rnnt-0.6b |
| Cosmos3-Edge | original | bf16 | | 33,127 | nvidia/Cosmos3-Edge |
| segformer-b3-finetuned-ade-512-512 | original | bf16 | | 32,787 | nvidia/segformer-b3-finetuned-ade-512-512 |
| DeepSeek-V3-0324-NVFP4 | nvfp4 | nvfp4 | | 31,794 | deepseek-ai/DeepSeek-V3-0324 |
| Qwen3.5-397B-A17B-NVFP4-V2 | nvfp4 | nvfp4 | | 31,590 | Qwen/Qwen3.5-397B-A17B |
| nemotron-colembed-vl-4b-v2 | original | bf16 | | 30,733 | nvidia/nemotron-colembed-vl-4b-v2 |
| Mistral-Medium-3.5-128B-NVFP4 | nvfp4 | nvfp4 | | 29,853 | mistralai/Mistral-Medium-3.5-128B |
| segformer-b4-finetuned-ade-512-512 | original | bf16 | | 29,578 | nvidia/segformer-b4-finetuned-ade-512-512 |
| MiniMax-M2.5-NVFP4 | nvfp4 | nvfp4 | | 28,995 | MiniMaxAI/MiniMax-M2.5 |
| Alpamayo-R1-10B | original | bf16 | | 28,723 | nvidia/Alpamayo-R1-10B |
| Cosmos-Reason1-7B | original | bf16 | | 28,385 | Qwen/Qwen2.5-VL-7B-Instruct |
| Minitron-8B-Base | original | bf16 | | 28,058 | nvidia/Minitron-8B-Base |
| GLM-5.1-NVFP4 | nvfp4 | nvfp4 | | 27,705 | zai-org/GLM-5.1 |
| bigvgan_v2_24khz_100band_256x | original | bf16 | | 26,934 | nvidia/bigvgan_v2_24khz_100band_256x |
| Cosmos-Predict2.5-2B | original | bf16 | | 26,219 | nvidia/Cosmos-Predict2.5-2B |
| GR00T-N1.6-3B | original | bf16 | | 26,007 | nvidia/GR00T-N1.6-3B |
| Qwen2.5-VL-7B-Instruct-NVFP4 | nvfp4 | nvfp4 | | 25,660 | Qwen/Qwen2.5-VL-7B-Instruct |
| KVzap-mlp-Llama-3.1-8B-Instruct | original | bf16 | | 24,315 | nvidia/KVzap-mlp-Llama-3.1-8B-Instruct |
| NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-FP8 | fp8 | fp8 | | 23,459 | nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16 |
| Llama-3_3-Nemotron-Super-49B-v1_5-NVFP4 | nvfp4 | nvfp4 | | 22,695 | nvidia/Llama-3_3-Nemotron-Super-49B-v1_5 |
| segformer-b0-finetuned-cityscapes-1024-1024 | original | bf16 | | 22,684 | nvidia/segformer-b0-finetuned-cityscapes-1024-1024 |
| NVIDIA-Nemotron-Nano-12B-v2-VL-FP8 | fp8 | fp8 | | 22,425 | nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16 |
| C-RADIO | original | bf16 | | 21,068 | nvidia/C-RADIO |
| segformer-b5-finetuned-cityscapes-1024-1024 | original | bf16 | | 19,998 | nvidia/segformer-b5-finetuned-cityscapes-1024-1024 |
| nemo-nano-codec-22khz-1.89kbps-21.5fps | original | bf16 | | 19,795 | nvidia/nemo-nano-codec-22khz-1.89kbps-21.5fps |
| NV-Embed-v2 | original | bf16 | | 19,122 | nvidia/NV-Embed-v2 |
| mit-b3 | original | bf16 | | 19,033 | nvidia/mit-b3 |
| RE-USE | original | bf16 | | 17,799 | nvidia/RE-USE |
| parakeet-ctc-0.6b | original | bf16 | | 16,874 | nvidia/parakeet-ctc-0.6b |
| Nemotron-H-56B-Base-8K | original | bf16 | | 16,431 | nvidia/Nemotron-H-56B-Base-8K |
| DAM-3B | original | bf16 | | 16,111 | Efficient-Large-Model/VILA1.5-3b |
| music-flamingo-hf | original | bf16 | | 15,523 | nvidia/music-flamingo-hf |
| Cosmos-H-Surgical | original | bf16 | | 14,926 | nvidia/Cosmos-Predict2.5-2B |
| Qwen3-235B-A22B-Instruct-2507-NVFP4 | nvfp4 | nvfp4 | | 14,506 | Qwen/Qwen3-235B-A22B-Instruct-2507 |
| segformer-b2-finetuned-cityscapes-1024-1024 | original | bf16 | | 13,895 | nvidia/segformer-b2-finetuned-cityscapes-1024-1024 |
| Kimi-K2-Thinking-NVFP4 | nvfp4 | nvfp4 | | 13,139 | moonshotai/Kimi-K2-Thinking |
| NVIDIA-Nemotron-Nano-9B-v2-NVFP4 | nvfp4 | nvfp4 | | 12,753 | nvidia/NVIDIA-Nemotron-Nano-9B-v2 |
| C-RADIOv4-H | original | bf16 | | 12,397 | nvidia/C-RADIOv4-H |
| Cosmos-Transfer2.5-2B | original | bf16 | | 12,246 | nvidia/Cosmos-Transfer2.5-2B |
| Nemotron-3-Embed-1B-NVFP4 | nvfp4 | nvfp4 | | 12,161 | nvidia/Nemotron-3-Embed-1B-BF16 |
| gliner-PII | original | bf16 | | 11,975 | nvidia/gliner-PII |
| Mistral-NeMo-Minitron-8B-Base | original | bf16 | | 11,726 | nvidia/Mistral-NeMo-Minitron-8B-Base |
| diar_sortformer_4spk-v1 | original | bf16 | | 11,667 | nvidia/diar_sortformer_4spk-v1 |
| omni-dreams-models | original | bf16 | | 11,466 | nvidia/Cosmos-Predict2.5-2B |
| Nemotron-Labs-Diffusion-14B | original | bf16 | | 11,024 | nvidia/Nemotron-Labs-Diffusion-14B |
| Llama3-ChatQA-1.5-8B | original | bf16 | | 10,891 | nvidia/Llama3-ChatQA-1.5-8B |
| difix | original | bf16 | | 10,863 | nvidia/difix |
| nemotron-colembed-vl-8b-v2 | original | bf16 | | 10,765 | nvidia/nemotron-colembed-vl-8b-v2 |
| difix_ref | original | bf16 | | 10,756 | nvidia/difix_ref |
| mit-b5 | original | bf16 | | 10,512 | nvidia/mit-b5 |
| Eagle2-2B | merge | merge | | 10,455 | google/paligemma-3b-mix-448 |
| Qwen3-VL-235B-A22B-Instruct-NVFP4-MLPerf-Inference-Closed-V6.0 | nvfp4 | nvfp4 | | 10,408 | Qwen/Qwen3-VL-235B-A22B-Instruct |
| C-RADIOv4-SO400M | original | bf16 | | 10,198 | nvidia/C-RADIOv4-SO400M |
| mit-b1 | original | bf16 | | 10,149 | nvidia/mit-b1 |
| C-RADIOv2-H | original | bf16 | | 9,639 | nvidia/C-RADIOv2-H |
| NVIDIA-Nemotron-Nano-9B-v2-Base | original | bf16 | | 9,533 | nvidia/NVIDIA-Nemotron-Nano-9B-v2-Base |
| omni-embed-nemotron-3b | original | bf16 | | 9,484 | nvidia/omni-embed-nemotron-3b |
| OpenReasoning-Nemotron-32B | original | bf16 | | 9,429 | Qwen/Qwen2.5-32B |
| prompt-task-and-complexity-classifier | original | bf16 | | 9,252 | nvidia/prompt-task-and-complexity-classifier |
| Cosmos-Predict2.5-14B | original | bf16 | | 9,185 | nvidia/Cosmos-Predict2.5-14B |
| Cosmos-Transfer1-7B-Sample-AV-Single2MultiView | original | bf16 | | 9,164 | nvidia/Cosmos-Transfer1-7B-Sample-AV-Single2MultiView |
| NVIDIA-Nemotron-3-Nano-4B-GGUF | gguf | gguf | | 8,952 | nvidia/NVIDIA-Nemotron-3-Nano-4B-FP8 |
| NV-Segment-CT | original | bf16 | | 8,642 | nvidia/NV-Segment-CT |
| Nemotron-Content-Safety-Reasoning-4B | original | bf16 | | 8,573 | google/gemma-3-4b-it |
| domain-classifier | original | bf16 | | 8,104 | nvidia/domain-classifier |
| gpt-oss-120b-Eagle3-long-context | original | bf16 | | 7,750 | openai/gpt-oss-120b |
| segformer-b0-finetuned-cityscapes-512-1024 | original | bf16 | | 7,571 | nvidia/segformer-b0-finetuned-cityscapes-512-1024 |
| Llama-3.1-70B-Instruct-FP8 | fp8 | fp8 | | 7,537 | meta-llama/Llama-3.1-70B-Instruct |
| nemocurator-fineweb-nemotron-4-edu-classifier | original | bf16 | | 7,421 | nvidia/nemocurator-fineweb-nemotron-4-edu-classifier |
| groupvit-gcc-yfcc | original | bf16 | | 7,272 | nvidia/groupvit-gcc-yfcc |
| DeepSeek-V3.2-NVFP4 | nvfp4 | nvfp4 | | 7,150 | deepseek-ai/DeepSeek-V3.2 |
| Cosmos-Embed1-448p-anomaly-detection | lora | lora | | 6,939 | — |
| nemotron-ocr-v2 | original | bf16 | | 6,871 | nvidia/nemotron-ocr-v2 |
| Qwen3-VL-235B-A22B-Instruct-NVFP4-MLPerf-Inference-Closed-V6.1 | nvfp4 | nvfp4 | | 6,643 | Qwen/Qwen3-VL-235B-A22B-Instruct |
| parakeet-rnnt-1.1b | original | bf16 | | 6,561 | nvidia/parakeet-rnnt-1.1b |
| Nemotron-3.5-Content-Safety | original | bf16 | | 6,485 | nvidia/Nemotron-3.5-Content-Safety |
| Cosmos3-Super-Image2Video | original | bf16 | | 6,467 | nvidia/Cosmos3-Super-Image2Video |
| magpie_tts_multilingual_357m | original | bf16 | | 6,072 | nvidia/magpie_tts_multilingual_357m |
| NVIDIA-Nemotron-3-Super-120B-A12B-Base-BF16 | original | bf16 | | 5,939 | nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-Base-BF16 |
| gpt-oss-120b-Eagle3-short-context | original | bf16 | | 5,598 | openai/gpt-oss-120b |
| audio-flamingo-next-hf | original | bf16 | | 5,528 | nvidia/audio-flamingo-next-hf |
| parakeet-tdt-1.1b | original | bf16 | | 5,523 | nvidia/parakeet-tdt-1.1b |
| Mistral-NeMo-Minitron-8B-Instruct | original | bf16 | | 5,413 | nvidia/Mistral-NeMo-Minitron-8B-Base |
| Nemotron-Labs-Diffusion-14B-Base | original | bf16 | | 5,369 | nvidia/Nemotron-Labs-Diffusion-14B-Base |
| canary-1b-flash | original | bf16 | | 5,253 | nvidia/canary-1b-flash |
| AceReason-Nemotron-7B | original | bf16 | | 5,122 | nvidia/AceReason-Nemotron-7B |
| parakeet-tdt_ctc-0.6b-ja | original | bf16 | | 5,052 | nvidia/parakeet-tdt_ctc-0.6b-ja |
| gpt-oss-120b-Eagle3-v3 | original | bf16 | | 4,988 | openai/gpt-oss-120b |
| GLM-4.7-NVFP4 | nvfp4 | nvfp4 | | 4,945 | zai-org/GLM-4.7 |
| mit-b4 | original | bf16 | | 4,903 | nvidia/mit-b4 |
| stt_en_conformer_transducer_large | original | bf16 | | 4,801 | nvidia/stt_en_conformer_transducer_large |
| Cosmos-Embed1-448p | original | bf16 | | 4,678 | nvidia/Cosmos-Embed1-448p |
| NVIDIA-Nemotron-Nano-9B-v2-Japanese | original | bf16 | | 4,431 | nvidia/NVIDIA-Nemotron-Nano-9B-v2 |
| Qwen3-8B-FP8 | fp8 | fp8 | | 4,389 | Qwen/Qwen3-8B |
| Nemotron-Labs-TwoTower-30B-A3B-Base-BF16 | original | bf16 | | 4,375 | nvidia/Nemotron-Labs-TwoTower-30B-A3B-Base-BF16 |
| Kimi-K2.6-Eagle3 | original | bf16 | | 4,366 | moonshotai/Kimi-K2.6 |
| Lyra-2.0 | original | bf16 | | 4,350 | nvidia/Lyra-2.0 |
| audio-flamingo-next-think-hf | original | bf16 | | 4,305 | nvidia/audio-flamingo-next-think-hf |
| Qwen3-VL-235B-A22B-Instruct-NVFP4 | nvfp4 | nvfp4 | | 4,288 | Qwen/Qwen3-VL-235B-A22B-Instruct |
| esm2_t33_650M_UR50D | original | bf16 | | 4,209 | nvidia/esm2_t33_650M_UR50D |
| MambaVision-L3-256-21K | original | bf16 | | 4,125 | nvidia/MambaVision-L3-256-21K |
| bigvgan_v2_22khz_80band_fmax8k_256x | original | bf16 | | 4,101 | nvidia/bigvgan_v2_22khz_80band_fmax8k_256x |
| stt_en_conformer_ctc_large | original | bf16 | | 4,075 | nvidia/stt_en_conformer_ctc_large |
| MambaVision-T-1K | original | bf16 | | 4,036 | nvidia/MambaVision-T-1K |
| Nemotron-Terminal-8B | original | bf16 | | 4,021 | nvidia/Nemotron-Terminal-8B |
| NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-BF16 | original | bf16 | | 3,851 | nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16 |
| Frame_VAD_Multilingual_MarbleNet_v2.0 | original | bf16 | | 3,845 | nvidia/Frame_VAD_Multilingual_MarbleNet_v2.0 |
| Kimi-K2.6-DFlash | original | bf16 | | 3,832 | moonshotai/Kimi-K2.6 |
| Nemotron-H-4B-Base-8K | original | bf16 | | 3,762 | nvidia/Nemotron-H-4B-Base-8K |
| Cosmos-Reason2-32B | original | bf16 | | 3,686 | Qwen/Qwen3-VL-32B-Instruct |
| MambaVision-B-21K | original | bf16 | | 3,680 | nvidia/MambaVision-B-21K |
| NVIDIA-Nemotron-Labs-3-Elastic-30B-A3B-BF16 | original | bf16 | | 3,604 | nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 |
| Llama-3.1-Nemotron-Nano-4B-v1.1 | original | bf16 | | 3,512 | nvidia/Llama-3.1-Minitron-4B-Width-Base |
| parakeet-tdt_ctc-110m | original | bf16 | | 3,496 | nvidia/parakeet-tdt_ctc-110m |
| NL-Diffusion-Image | original | bf16 | | 3,478 | nvidia/NL-Diffusion-Image |
| quality-classifier-deberta | original | bf16 | | 3,477 | nvidia/quality-classifier-deberta |
| Llama-3.1-405B-Instruct-FP8 | fp8 | fp8 | | 3,420 | meta-llama/Llama-3.1-405B-Instruct |
| Riva-Translate-4B-Instruct-v1.1 | original | bf16 | | 3,394 | nvidia/Mistral-NeMo-12B-Base |
| llama-3.1-nemoguard-8b-topic-control | original | bf16 | | 3,334 | meta-llama/Llama-3.1-8B-Instruct |
| Harmonizer | original | bf16 | | 3,329 | nvidia/Harmonizer |
| Aegis-AI-Content-Safety-LlamaGuard-Defensive-1.0 | original | bf16 | | 3,293 | nvidia/Aegis-AI-Content-Safety-LlamaGuard-Defensive-1.0 |
| Kimodo-SOMA-RP-v1.1 | original | bf16 | | 3,173 | nvidia/Kimodo-SOMA-RP-v1.1 |
| Cosmos3-Nano-Policy-DROID | original | bf16 | | 2,977 | nvidia/Cosmos3-Nano-Policy-DROID |
| Llama-3_1-Nemotron-Ultra-253B-v1 | original | bf16 | | 2,928 | nvidia/Llama-3_1-Nemotron-Ultra-253B-v1 |
| segformer-b1-finetuned-cityscapes-1024-1024 | original | bf16 | | 2,892 | nvidia/segformer-b1-finetuned-cityscapes-1024-1024 |
| NV-Raw2insights-MRI | original | bf16 | | 2,881 | nvidia/NV-Raw2insights-MRI |
| Nemotron-Research-Reasoning-Qwen-1.5B | original | bf16 | | 2,786 | deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B |
| esm2_t48_15B_UR50D | original | bf16 | | 2,750 | nvidia/esm2_t48_15B_UR50D |
| Nemotron-Labs-Audex-2B | original | bf16 | | 2,749 | nvidia/Nemotron-Labs-Audex-2B |
| Nemotron-Labs-Audex-30B-A3B | original | bf16 | | 2,740 | nvidia/Nemotron-Labs-Audex-30B-A3B |
| OpenReasoning-Nemotron-1.5B | original | bf16 | | 2,738 | Qwen/Qwen2.5-1.5B |
| stt_en_fastconformer_hybrid_large_pc | original | bf16 | | 2,731 | nvidia/stt_en_fastconformer_hybrid_large_pc |
| multilingual-domain-classifier | original | bf16 | | 2,724 | nvidia/multilingual-domain-classifier |
| Minitron-4B-Base | original | bf16 | | 2,721 | nvidia/Minitron-4B-Base |
| Hymba-1.5B-Base | original | bf16 | | 2,686 | nvidia/Hymba-1.5B-Base |
| stt_en_fastconformer_ctc_large | original | bf16 | | 2,615 | nvidia/stt_en_fastconformer_ctc_large |
| DeepSeek-R1-NVFP4 | nvfp4 | nvfp4 | | 2,526 | deepseek-ai/DeepSeek-R1 |
| Cosmos3-Super-Text2Image | original | bf16 | | 2,520 | nvidia/Cosmos3-Super-Text2Image |
| canary-1b | original | bf16 | | 2,457 | nvidia/canary-1b |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-GenRM | original | bf16 | | 2,420 | NVIDIA/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 |
| NVIDIA-Nemotron-Nano-12B-v2-Base | original | bf16 | | 2,411 | nvidia/NVIDIA-Nemotron-Nano-12B-v2-Base |
| Llama-3.1-Minitron-4B-Width-Base | original | bf16 | | 2,339 | nvidia/Llama-3.1-Minitron-4B-Width-Base |
| Nemotron-Orchestrator-8B | original | bf16 | | 2,271 | Qwen/Qwen3-8B |
| segformer-b3-finetuned-cityscapes-1024-1024 | original | bf16 | | 2,265 | nvidia/segformer-b3-finetuned-cityscapes-1024-1024 |
| Ising-Decoder-SurfaceCode-1-Fast | original | bf16 | | 2,265 | nvidia/Ising-Decoder-SurfaceCode-1-Fast |
| fourcastnet1 | original | bf16 | | 2,248 | nvidia/fourcastnet1 |
| segformer-b4-finetuned-cityscapes-1024-1024 | original | bf16 | | 2,207 | nvidia/segformer-b4-finetuned-cityscapes-1024-1024 |
| llama-nv-embed-reasoning-3b | original | bf16 | | 2,141 | meta-llama/Llama-3.2-3B |
| Kimi-K2.7-Code-DFlash | original | bf16 | | 2,128 | moonshotai/Kimi-K2.7-Code |
| Nemotron-H-8B-Reasoning-128K | original | bf16 | | 2,020 | nvidia/Nemotron-H-8B-Reasoning-128K |
| GN1x-Tuned-Arena-G1-Static-PickNPlace | original | bf16 | | 2,020 | nvidia/GR00T-N1.7-3B |
| Kimi-K2.5-Thinking-Eagle3 | original | bf16 | | 2,019 | moonshotai/Kimi-K2.5 |
| Cosmos-Tokenize1-CV8x8x8-720p | original | bf16 | | 1,932 | nvidia/Cosmos-Tokenize1-CV8x8x8-720p |
| Qwen3-Next-80B-A3B-Thinking-NVFP4 | nvfp4 | nvfp4 | | 1,912 | Qwen/Qwen3-Next-80B-A3B-Thinking |
| DeepSeek-R1-0528-NVFP4 | nvfp4 | nvfp4 | | 1,910 | deepseek-ai/DeepSeek-R1-0528 |
| OpenReasoning-Nemotron-14B | original | bf16 | | 1,843 | Qwen/Qwen2.5-14B |
| ARDY-Core-RP-20FPS-Horizon40 | original | bf16 | | 1,830 | nvidia/ARDY-Core-RP-20FPS-Horizon40 |
| stt_ar_fastconformer_hybrid_large_pcd_v1.0 | original | bf16 | | 1,812 | nvidia/stt_ar_fastconformer_hybrid_large_pcd_v1.0 |
| canary-180m-flash | original | bf16 | | 1,807 | nvidia/canary-180m-flash |
| Cosmos-Transfer1-7B | original | bf16 | | 1,793 | nvidia/Cosmos-Transfer1-7B |
| AceReason-Nemotron-1.1-7B | original | bf16 | | 1,771 | nvidia/AceReason-Nemotron-1.1-7B |
| GR00T-N1.6-fractal | original | bf16 | | 1,707 | nvidia/GR00T-N1.6-3B |
| Cosmos-UpsamplePrompt1-12B-Text2World | original | bf16 | | 1,682 | nvidia/Cosmos-UpsamplePrompt1-12B-Text2World |
| C-RADIOv3-H | original | bf16 | | 1,654 | nvidia/C-RADIOv3-H |
| GR00T-N1.5-3B | original | bf16 | | 1,638 | nvidia/GR00T-N1.5-3B |
| Cosmos-Embed1-224p | original | bf16 | | 1,576 | nvidia/Cosmos-Embed1-224p |
| Nemotron-H-4B-Instruct-128K | original | bf16 | | 1,535 | nvidia/Nemotron-H-4B-Base-8K |
| Qwen3-Coder-480B-A35B-Instruct-NVFP4 | nvfp4 | nvfp4 | | 1,527 | Qwen/Qwen3-Coder-480B-A35B-Instruct |
| MiniMax-M2.7-DFlash | original | bf16 | | 1,508 | MiniMaxAI/MiniMax-M2.7 |
| Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct | original | bf16 | | 1,488 | nvidia/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct |
| Aegis-AI-Content-Safety-LlamaGuard-Permissive-1.0 | original | bf16 | | 1,483 | nvidia/Aegis-AI-Content-Safety-LlamaGuard-Permissive-1.0 |
| Kimodo-SOMA-RP-v1 | original | bf16 | | 1,477 | nvidia/Kimodo-SOMA-RP-v1 |
| music-flamingo-think-2601-hf | original | bf16 | | 1,444 | nvidia/music-flamingo-think-2601-hf |
| C-RADIOv3-B | original | bf16 | | 1,419 | nvidia/C-RADIOv3-B |
| OpenReasoning-Nemotron-7B | original | bf16 | | 1,403 | Qwen/Qwen2.5-7B |
| MambaVision-B-1K | original | bf16 | | 1,386 | nvidia/MambaVision-B-1K |
| OpenMath2-Llama3.1-8B | original | bf16 | | 1,383 | meta-llama/Llama-3.1-8B |
| audio-flamingo-next-captioner-hf | original | bf16 | | 1,359 | nvidia/audio-flamingo-next-captioner-hf |
| Nemotron-Cascade-14B-Thinking | original | bf16 | | 1,343 | nvidia/Nemotron-Cascade-14B-Thinking |
| nemo-nano-codec-22khz-0.6kbps-12.5fps | original | bf16 | | 1,340 | nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps |
| OpenMath-Nemotron-1.5B | original | bf16 | | 1,329 | Qwen/Qwen2.5-Math-1.5B |
| Llama-3_1-Nemotron-51B-Instruct | original | bf16 | | 1,308 | nvidia/Llama-3_1-Nemotron-51B-Instruct |
| stt_es_fastconformer_hybrid_large_pc | original | bf16 | | 1,273 | nvidia/stt_es_fastconformer_hybrid_large_pc |
| Cosmos-1.0-Diffusion-7B-Video2World | original | bf16 | | 1,258 | nvidia/Cosmos-1.0-Diffusion-7B-Video2World |
| fourcastnet3 | original | bf16 | | 1,255 | nvidia/fourcastnet3 |
| Nemotron-3-Content-Safety | original | bf16 | | 1,252 | google/gemma-3-4b-it |
| bigvgan_base_24khz_100band | original | bf16 | | 1,243 | nvidia/bigvgan_base_24khz_100band |
| GR00T-N1.7-DROID | original | bf16 | | 1,232 | nvidia/GR00T-N1.7-DROID |
| Cosmos-Guardrail1 | original | bf16 | | 1,228 | nvidia/Cosmos-Guardrail1 |
| gpt-oss-120b-Eagle3-throughput | original | bf16 | | 1,214 | openai/gpt-oss-120b |
| Qwen3-235B-A22B-Thinking-2507-NVFP4 | nvfp4 | nvfp4 | | 1,186 | Qwen/Qwen3-235B-A22B-Thinking-2507 |
| bigvgan_v2_44khz_128band_256x | original | bf16 | | 1,160 | nvidia/bigvgan_v2_44khz_128band_256x |
| C-RADIOv3-L | original | bf16 | | 1,153 | nvidia/C-RADIOv3-L |
| Qwen3-Nemotron-32B-GenRM-Principle | original | bf16 | | 1,130 | Qwen/Qwen3-32B |
| Privasis-Cleaner-0.6B | original | bf16 | | 1,124 | Qwen/Qwen3-0.6B |
| Cosmos-Embed1-336p | original | bf16 | | 1,094 | nvidia/Cosmos-Embed1-336p |
| Kimodo-SMPLX-RP-v1 | original | bf16 | | 1,083 | nvidia/Kimodo-SMPLX-RP-v1 |
| Cosmos-1.0-Diffusion-7B-Text2World | original | bf16 | | 1,059 | nvidia/Cosmos-1.0-Diffusion-7B-Text2World |
| parakeet-unified-en-0.6b | original | bf16 | | 1,052 | nvidia/parakeet-unified-en-0.6b |
| stt_en_fastconformer_hybrid_large_streaming_multi | original | bf16 | | 1,048 | nvidia/stt_en_fastconformer_hybrid_large_streaming_multi |
| Ising-Calibration-1-35B-A3B | original | bf16 | | 1,042 | Qwen/Qwen3.5-35B-A3B |
| Llama-3.1-Minitron-4B-Depth-Base | original | bf16 | | 1,010 | nvidia/Llama-3.1-Minitron-4B-Depth-Base |
| Llama-3.1-Nemotron-Safety-Guard-8B-v3 | original | bf16 | | 1,009 | meta-llama/Llama-3.1-8B-Instruct |
| Qwen2.5-VL-7B-Instruct-FP8 | fp8 | fp8 | | 1,006 | Qwen/Qwen2.5-VL-7B-Instruct |
| Privasis-Cleaner-4B | original | bf16 | | 935 | Qwen/Qwen3-4B-Instruct-2507 |
| NVIDIA-Nemotron-Labs-3-Elastic-30B-A3B-NVFP4 | nvfp4 | nvfp4 | | 914 | nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 |
| llama-nemotron-colembed-vl-3b-v2 | original | bf16 | | 910 | nvidia/llama-nemotron-colembed-vl-3b-v2 |
| AutoGaze | original | bf16 | | 909 | nvidia/AutoGaze |
| Eagle2-1B | merge | merge | | 894 | google/paligemma-3b-mix-448 |
| GR00T-N1.7-SimplerEnv-Bridge | original | bf16 | | 889 | nvidia/GR00T-N1.7-SimplerEnv-Bridge |
| parakeet-tdt_ctc-1.1b | original | bf16 | | 879 | nvidia/parakeet-tdt_ctc-1.1b |
| Llama-3_3-Nemotron-Super-49B-v1-FP8 | fp8 | fp8 | | 873 | nvidia/Llama-3_3-Nemotron-Super-49B-v1 |
| parakeet-ctc-0.6b-Vietnamese | original | bf16 | | 873 | nvidia/parakeet-ctc-0.6b-Vietnamese |
| NV-Segment-CTMR | original | bf16 | | 866 | nvidia/NV-Segment-CTMR |
| stt_en_conformer_ctc_small | original | bf16 | | 863 | nvidia/stt_en_conformer_ctc_small |
| content-type-classifier-deberta | original | bf16 | | 828 | nvidia/content-type-classifier-deberta |
| NV-Embed-v1 | original | bf16 | | 819 | nvidia/NV-Embed-v1 |
| bigvgan_22khz_80band | original | bf16 | | 804 | nvidia/bigvgan_22khz_80band |
| nemotron-labs-audio-visual-flamingo-hf | original | bf16 | | 802 | nvidia/nemotron-labs-audio-visual-flamingo-hf |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-Base-BF16 | original | bf16 | | 801 | nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-Base-BF16 |
| Qwen3-Nemotron-235B-A22B-GenRM-2603 | original | bf16 | | 799 | Qwen/Qwen3-235B-A22B-Thinking-2507 |
| Phi-4-reasoning-plus-FP8 | fp8 | fp8 | | 766 | microsoft/Phi-4-reasoning-plus |
| stt_kk_ru_fastconformer_hybrid_large | original | bf16 | | 763 | nvidia/stt_kk_ru_fastconformer_hybrid_large |
| NV-Reason-CXR-3B | original | bf16 | | 755 | Qwen/Qwen2.5-VL-3B-Instruct |
| EGM-4B-SFT | original | bf16 | | 750 | Qwen/Qwen3-VL-4B-Thinking |
| ARDY-Core-RP-20FPS-Horizon8 | original | bf16 | | 740 | nvidia/ARDY-Core-RP-20FPS-Horizon8 |
| Llama-3_1-Nemotron-Ultra-253B-v1-FP8 | fp8 | fp8 | | 734 | nvidia/Llama-3_1-Nemotron-Ultra-253B-v1 |
| Llama-3.1-405B-Instruct-NVFP4 | nvfp4 | nvfp4 | | 716 | meta-llama/Llama-3.1-405B-Instruct |
| nemocurator-fineweb-mixtral-edu-classifier | original | bf16 | | 714 | nvidia/nemocurator-fineweb-mixtral-edu-classifier |
| dvlt | original | bf16 | | 691 | facebook/dinov2-base |
| vgg-ttt | original | bf16 | | 687 | facebook/VGGT-1B |
| multitalker-parakeet-streaming-0.6b-v1 | original | bf16 | | 677 | nvidia/multitalker-parakeet-streaming-0.6b-v1 |
| AMPLIFY_120M | original | bf16 | | 674 | nvidia/AMPLIFY_120M |
| GR00T-N1.7-SimplerEnv-Fractal | original | bf16 | | 660 | nvidia/GR00T-N1.7-SimplerEnv-Fractal |
| Cosmos-1.0-Diffusion-14B-Text2World | original | bf16 | | 642 | nvidia/Cosmos-1.0-Diffusion-14B-Text2World |
| OpenMath-Nemotron-7B | original | bf16 | | 636 | Qwen/Qwen2.5-Math-7B |
| stt_de_fastconformer_hybrid_large_pc | original | bf16 | | 636 | nvidia/stt_de_fastconformer_hybrid_large_pc |
| Cosmos3-Super-Image2Video-4Step | original | bf16 | | 621 | nvidia/Cosmos3-Super-Image2Video-4Step |
| stt_uk_citrinet_1024_gamma_0_25 | original | bf16 | | 620 | nvidia/stt_uk_citrinet_1024_gamma_0_25 |
| Nemotron-Flash-1B | original | bf16 | | 617 | nvidia/Nemotron-Flash-1B |
| Real-time_RE-USE | original | bf16 | | 608 | nvidia/Real-time_RE-USE |
| instruction-data-guard | original | bf16 | | 606 | nvidia/instruction-data-guard |
| Qwen3-235B-A22B-FP8 | fp8 | fp8 | | 603 | Qwen/Qwen3-235B-A22B |
| stt_en_conformer_transducer_xlarge | original | bf16 | | 600 | nvidia/stt_en_conformer_transducer_xlarge |
| OpenCodeReasoning-Nemotron-7B | original | bf16 | | 593 | Qwen/Qwen2.5-7B-Instruct |
| stt_fr_fastconformer_hybrid_large_pc | original | bf16 | | 587 | nvidia/stt_fr_fastconformer_hybrid_large_pc |
| Kimodo-G1-RP-v1 | original | bf16 | | 581 | nvidia/Kimodo-G1-RP-v1 |
| C-RADIOv2-B | original | bf16 | | 576 | nvidia/C-RADIOv2-B |
| Nemotron-4-Mini-Hindi-4B-Instruct | original | bf16 | | 556 | nvidia/Nemotron-4-Mini-Hindi-4B-Base |
| DLER-R1-1.5B-Research | original | bf16 | | 550 | deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B |
| AMPLIFY_350M | original | bf16 | | 547 | nvidia/AMPLIFY_350M |
| DAM-3B-Video | original | bf16 | | 540 | Efficient-Large-Model/VILA1.5-3b |
| bigvgan_base_22khz_80band | original | bf16 | | 539 | nvidia/bigvgan_base_22khz_80band |
| Cosmos-Predict2-2B-Text2Image | original | bf16 | | 525 | nvidia/Cosmos-Predict2-2B-Text2Image |
| MM-Embed | original | bf16 | | 523 | nvidia/MM-Embed |
| llama-3.1-nemoguard-8b-content-safety | original | bf16 | | 523 | meta-llama/Llama-3.1-8B-Instruct |
| Llama3-ChatQA-2-8B | original | bf16 | | 514 | nvidia/Llama3-ChatQA-2-8B |
| AceReason-Nemotron-14B | original | bf16 | | 513 | nvidia/AceReason-Nemotron-14B |
| Nemotron-Labs-Diffusion-VLM-8B | original | bf16 | | 512 | nvidia/Nemotron-Labs-Diffusion-VLM-8B |
| llama-nemotron-embed-vl-1b-v2-fp8 | fp8 | fp8 | | 487 | nvidia/llama-nemotron-embed-vl-1b-v2 |
| parakeet_realtime_eou_120m-v1 | original | bf16 | | 486 | nvidia/parakeet_realtime_eou_120m-v1 |
| Nemotron-Cascade-8B | original | bf16 | | 485 | nvidia/Nemotron-Cascade-8B |
| omnivinci | original | bf16 | | 481 | nvidia/omnivinci |
| Qwen2.5-VL-7B-Surg-CholecT50 | original | bf16 | | 480 | Qwen/Qwen2.5-VL-7B |
| stt_pl_fastconformer_hybrid_large_pc | original | bf16 | | 471 | nvidia/stt_pl_fastconformer_hybrid_large_pc |
| VILA-HD-8B-PS3-1.5K-SigLIP2 | original | bf16 | | 465 | nvidia/VILA-HD-8B-PS3-1.5K-SigLIP2 |
| audio-flamingo-3 | original | bf16 | | 461 | nvidia/audio-flamingo-3 |
| Cosmos-Tokenize1-DV8x16x16-720p | original | bf16 | | 459 | nvidia/Cosmos-Tokenize1-DV8x16x16-720p |
| GR00T-N1.6-bridge | original | bf16 | | 454 | nvidia/GR00T-N1.6-3B |
| stt_ar_fastconformer_hybrid_large_pc_v1.0 | original | bf16 | | 451 | nvidia/stt_ar_fastconformer_hybrid_large_pc_v1.0 |
| GR00T-H | original | bf16 | | 451 | nvidia/GR00T-N1.6-3B |
| C-RADIOv2-L | original | bf16 | | 446 | nvidia/C-RADIOv2-L |
| Nemotron-Cascade-8B-Thinking | original | bf16 | | 440 | nvidia/Nemotron-Cascade-8B-Thinking |
| smolvla-arena-gr1-microwave | original | bf16 | | 437 | lerobot/smolvla_base |
| Cosmos-1.0-Guardrail | original | bf16 | | 435 | nvidia/Cosmos-1.0-Guardrail |
| Audio2Face-3D-v3.0 | original | bf16 | | 434 | nvidia/Audio2Face-3D-v3.0 |
| MambaVision-S-1K | original | bf16 | | 433 | nvidia/MambaVision-S-1K |
| Hymba-1.5B-Instruct | original | bf16 | | 431 | nvidia/Hymba-1.5B-Base |
| NV-GenMol-89M-v1 | original | bf16 | | 425 | nvidia/NV-GenMol-89M-v1 |
| stormscope-goes-mrms | original | bf16 | | 422 | nvidia/stormscope-goes-mrms |
| Cosmos-Transfer1-7B-Sample-AV | original | bf16 | | 414 | nvidia/Cosmos-Transfer1-7B-Sample-AV |
| AceMath-7B-Instruct | original | bf16 | | 412 | nvidia/AceMath-7B-Instruct |
| Cosmos-Predict2-0.6B-Text2Image | original | bf16 | | 403 | nvidia/Cosmos-Predict2-0.6B-Text2Image |
| stt_ru_fastconformer_hybrid_large_pc | original | bf16 | | 390 | nvidia/stt_ru_fastconformer_hybrid_large_pc |
| DAM-3B-Self-Contained | original | bf16 | | 389 | Efficient-Large-Model/VILA1.5-3b |
| parakeet-rnnt-110m-da-dk | original | bf16 | | 382 | nvidia/parakeet-rnnt-110m-da-dk |
| Qwen3-235B-A22B-Eagle3 | original | bf16 | | 377 | Qwen/Qwen3-235B-A22B |
| Cosmos-0.1-Tokenizer-DI16x16 | original | bf16 | | 374 | nvidia/Cosmos-0.1-Tokenizer-DI16x16 |
| segformer-b0-finetuned-cityscapes-640-1280 | original | bf16 | | 371 | nvidia/segformer-b0-finetuned-cityscapes-640-1280 |
| Cosmos3-Super-Text2Image-4Step | original | bf16 | | 364 | nvidia/Cosmos3-Super-Text2Image-4Step |
| ARDY-G1-RP-25FPS-Horizon52 | original | bf16 | | 363 | nvidia/ARDY-G1-RP-25FPS-Horizon52 |
| nemotron-table-structure-v1 | original | bf16 | | 360 | nvidia/nemotron-table-structure-v1 |
| NV-Generate-MR-Brain | original | bf16 | | 360 | nvidia/NV-Generate-MR-Brain |
| Nemotron-Terminal-14B | original | bf16 | | 358 | nvidia/Nemotron-Terminal-14B |
| EGM-8B-SFT | original | bf16 | | 357 | Qwen/Qwen3-VL-8B-Thinking |
| Nemotron-4-Mini-Hindi-4B-Base | original | bf16 | | 355 | nvidia/Minitron-4B-Base |
| Qwen3-Nemotron-8B-BRRM | original | bf16 | | 351 | Qwen/Qwen3-8B |
| GR00T-H-N1.7 | original | bf16 | | 347 | nvidia/GR00T-N1.7-3B |
| GR00T-N1.6-DROID | original | bf16 | | 340 | nvidia/GR00T-N1.6-3B |
| PiD | original | bf16 | | 337 | nvidia/PixelDiT-1300M-1024px |
| segformer-b0-finetuned-cityscapes-768-768 | original | bf16 | | 336 | nvidia/segformer-b0-finetuned-cityscapes-768-768 |
| NVIDIA-Nemotron-Parse-v1.1-TC | original | bf16 | | 325 | nvidia/NVIDIA-Nemotron-Parse-v1.1-TC |
| MiniMax-M3-DSpark | original | bf16 | | 323 | MiniMaxAI/MiniMax-M3 |
| Cosmos-Predict2-14B-Text2Image | original | bf16 | | 318 | nvidia/Cosmos-Predict2-14B-Text2Image |
| Fixer | original | bf16 | | 313 | nvidia/Fixer |
| bigvgan_24khz_100band | original | bf16 | | 312 | nvidia/bigvgan_24khz_100band |
| VideoITG-8B | merge | merge | | 310 | Qwen/Qwen2-7B-Instruct |
| instant-nurec | original | bf16 | | 310 | nvidia/instant-nurec |
| C-RADIOv2-g | original | bf16 | | 309 | nvidia/C-RADIOv2-g |
| Llama-3.1-Nemotron-8B-UltraLong-4M-Instruct | original | bf16 | | 305 | nvidia/Llama-3.1-Nemotron-8B-UltraLong-4M-Instruct |
| Cosmos3-Edge-Policy-DROID | original | bf16 | | 303 | nvidia/Cosmos3-Edge-Policy-DROID |
| Cosmos-Policy-LIBERO-Predict2-2B | original | bf16 | | 302 | nvidia/Cosmos-Predict2-2B-Video2World |
| Phi-4-multimodal-instruct-FP8 | fp8 | fp8 | | 296 | microsoft/Phi-4-multimodal-instruct |
| Nemotron-H-47B-Reasoning-128K | original | bf16 | | 295 | nvidia/Nemotron-H-47B-Reasoning-128K |
| Qwen-Image-Flash | original | bf16 | | 295 | Qwen/Qwen-Image |
| stt_fa_fastconformer_hybrid_large | original | bf16 | | 293 | nvidia/stt_fa_fastconformer_hybrid_large |
| NVILA-8B-HD-Video | original | bf16 | | 293 | nvidia/NVILA-8B-HD-Video |
| Nemotron-Terminal-32B | original | bf16 | | 289 | nvidia/Nemotron-Terminal-32B |
| RADIO-L | original | bf16 | | 287 | nvidia/RADIO-L |
| asset-harvester | original | bf16 | | 283 | nvidia/asset-harvester |
| GR00T-N1-2B | original | bf16 | | 281 | nvidia/GR00T-N1-2B |
| Llama-3.3-Nemotron-70B-Reward-Principle | original | bf16 | | 278 | meta-llama/Llama-3.3-70B-Instruct |
| ArtiFixer | original | bf16 | | 277 | nvidia/ArtiFixer |
| stt_it_fastconformer_hybrid_large_pc | original | bf16 | | 277 | nvidia/stt_it_fastconformer_hybrid_large_pc |
| NVIDIA-Nemotron-Labs-3-Elastic-30B-A3B-FP8 | fp8 | fp8 | | 276 | nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 |
| gr00t17-lerobot-libero_object-640 | original | bf16 | | 272 | nvidia/gr00t17-lerobot-libero_object-640 |
| Nemotron-H-47B-Base-8K | original | bf16 | | 271 | nvidia/Nemotron-H-56B-Base-8K |
| EGM-8B | original | bf16 | | 268 | Qwen/Qwen3-VL-8B-Thinking |
| Nemotron-4-340B-Base | original | bf16 | | 266 | nvidia/Nemotron-4-340B-Base |
| atlas-era5 | original | bf16 | | 266 | nvidia/atlas-era5 |
| low-frame-rate-speech-codec-22khz | original | bf16 | | 265 | nvidia/low-frame-rate-speech-codec-22khz |
| Cosmos-0.1-Tokenizer-CI8x8 | original | bf16 | | 263 | nvidia/Cosmos-0.1-Tokenizer-CI8x8 |
| gr00t17-lerobot-libero_spatial-640 | original | bf16 | | 262 | nvidia/gr00t17-lerobot-libero_spatial-640 |
| Qwen2.5-CascadeRL-RM-72B | original | bf16 | | 259 | nvidia/Qwen2.5-CascadeRL-RM-72B |
| RNAPro-Public-Best-500M | original | bf16 | | 258 | nvidia/RNAPro-Public-Best-500M |
| esm2_t6_8M_UR50D | original | bf16 | | 257 | nvidia/esm2_t6_8M_UR50D |
| Audio2Face-3D-v2.3-Mark | original | bf16 | | 257 | nvidia/Audio2Face-3D-v2.3-Mark |
| stt_ka_fastconformer_hybrid_large_pc | original | bf16 | | 255 | nvidia/stt_ka_fastconformer_hybrid_large_pc |
| MambaVision-T2-1K | original | bf16 | | 253 | nvidia/MambaVision-T2-1K |
| llama-nemoretriever-colembed-3b-v1 | original | bf16 | | 251 | nvidia/llama-nemoretriever-colembed-3b-v1 |
| NV-Generate-MR | original | bf16 | | 248 | nvidia/NV-Generate-MR |
| AnyFlow-FAR-Wan2.1-1.3B-Diffusers | original | bf16 | | 246 | Wan-AI/Wan2.1-T2V-1.3B-Diffusers |
| Audio2Face-3D-v2.3.1-Claire | original | bf16 | | 239 | nvidia/Audio2Face-3D-v2.3.1-Claire |
| gr00t17-lerobot-libero_10-640 | original | bf16 | | 239 | nvidia/gr00t17-lerobot-libero_10-640 |
| Qwen3-8B-DMS-8x | original | bf16 | | 238 | Qwen/Qwen3-8B |
| GR00T-N1.6-G1-PnPAppleToPlate | original | bf16 | | 237 | nvidia/GR00T-N1.6-3B |
| pi05-arena-gr1-microwave | original | bf16 | | 233 | nvidia/pi05-arena-gr1-microwave |
| C-RADIOv3-g | original | bf16 | | 228 | nvidia/C-RADIOv3-g |
| Cosmos-Predict2-14B-Video2World | original | bf16 | | 226 | nvidia/Cosmos-Predict2-14B-Video2World |
| GEN3C-Cosmos-7B | original | bf16 | | 222 | nvidia/GEN3C-Cosmos-7B |
| Diffusion_Renderer_Inverse_Cosmos_7B | original | bf16 | | 221 | nvidia/Diffusion_Renderer_Inverse_Cosmos_7B |
| Llama3-ChatQA-1.5-70B | original | bf16 | | 220 | nvidia/Llama3-ChatQA-1.5-70B |
| Audio2Face-3D-v2.3.1-James | original | bf16 | | 220 | nvidia/Audio2Face-3D-v2.3.1-James |
| Llama-3.1-Nemotron-70B-Reward-HF | original | bf16 | | 217 | meta-llama/Llama-3.1-70B-Instruct |
| AceMath-1.5B-Instruct | original | bf16 | | 215 | nvidia/AceMath-1.5B-Instruct |
| Nemotron-4-340B-Instruct | original | bf16 | | 209 | nvidia/Nemotron-4-340B-Instruct |
| OpenMath-Nemotron-32B | original | bf16 | | 209 | Qwen/Qwen2.5-32B |
| DeepSeek-R1-NVFP4-v2 | nvfp4 | nvfp4 | | 209 | deepseek-ai/DeepSeek-R1 |
| CUDA-Autocomplete | original | bf16 | | 207 | Qwen/Qwen2.5-Coder-7B |
| AceInstruct-7B | original | bf16 | | 206 | nvidia/AceInstruct-7B |
| gr00t17-lerobot-libero_goal-640 | original | bf16 | | 204 | nvidia/gr00t17-lerobot-libero_goal-640 |
| AceMath-7B-RM | original | bf16 | | 203 | nvidia/AceMath-7B-RM |
| Cosmos-0.1-Tokenizer-DI8x8 | original | bf16 | | 195 | nvidia/Cosmos-0.1-Tokenizer-DI8x8 |
| Llama-3.3-Nemotron-70B-Reward-Multilingual | original | bf16 | | 195 | meta-llama/Llama-3.3-70B-Instruct |
| Llama-3.3-70B-Instruct-Eagle3 | nvfp4 | nvfp4 | | 191 | nvidia/Llama-3.3-70B-Instruct-FP4 |
| NV-EmbedCode-7b-v1 | original | bf16 | | 190 | nvidia/NV-EmbedCode-7b-v1 |
| RADIO | original | bf16 | | 187 | nvidia/RADIO |
| PS3-4K-SigLIP2 | original | bf16 | | 185 | google/siglip2-so400m-patch14-384 |
| Riva-Translate-4B-Instruct | original | bf16 | | 181 | nvidia/Mistral-NeMo-12B-Base |
| Riva-Translate-4B-Instruct-v2 | original | bf16 | | 180 | nvidia/Mistral-NeMo-12B-Base |
| Kimodo-SOMA-SEED-v1.1 | original | bf16 | | 179 | nvidia/Kimodo-SOMA-SEED-v1.1 |
| C-RADIOv4-1D-H | original | bf16 | | 179 | nvidia/C-RADIOv4-1D-H |
| Cosmos-Policy-RoboCasa-Predict2-2B | original | bf16 | | 178 | nvidia/Cosmos-Predict2-2B-Video2World |
| tts_hifigan | original | bf16 | | 177 | nvidia/tts_hifigan |
| llama-nemoretriever-colembed-1b-v1 | original | bf16 | | 176 | nvidia/llama-nemoretriever-colembed-1b-v1 |
| stormcast-v1-era5-hrrr | original | bf16 | | 168 | nvidia/stormcast-v1-era5-hrrr |
| OpenCodeReasoning-Nemotron-32B | original | bf16 | | 163 | Qwen/Qwen2.5-32B-Instruct |
| Nemotron-Flash-3B-Instruct | original | bf16 | | 160 | nvidia/Nemotron-Flash-3B-Instruct |
| EGM-4B | original | bf16 | | 158 | Qwen/Qwen3-VL-4B-Thinking |
| Eagle2-9B | merge | merge | | 155 | google/paligemma-3b-mix-448 |
| AceInstruct-1.5B | original | bf16 | | 150 | nvidia/AceInstruct-1.5B |
| OpenMath-Nemotron-14B | original | bf16 | | 150 | Qwen/Qwen2.5-14B |
| GN1x-Tuned-Arena-G1-Loco-Manipulation | original | bf16 | | 150 | nvidia/GN1x-Tuned-Arena-G1-Loco-Manipulation |
| stt_en_fastconformer_transducer_large | original | bf16 | | 149 | nvidia/stt_en_fastconformer_transducer_large |
| Efficient-DLM-4B | original | bf16 | | 147 | nvidia/Efficient-DLM-4B |
| Cosmos-AnomalyGen-PCB-2B | original | bf16 | | 146 | nvidia/Cosmos-AnomalyGen-PCB-2B |
| Mistral-NeMo-12B-Instruct | original | bf16 | | 145 | nvidia/Mistral-NeMo-12B-Instruct |
| Nemotron-H-8B-Reasoning-128K-FP8 | fp8 | fp8 | | 145 | nvidia/Nemotron-H-8B-Reasoning-128K |
| NV-La-Proteina-Ucond-v1 | original | bf16 | | 145 | nvidia/NV-La-Proteina-Ucond-v1 |
| geotransolver_drivaerml | original | bf16 | | 141 | nvidia/geotransolver_drivaerml |
| ARDY-G1-RP-25FPS-Horizon8 | original | bf16 | | 141 | nvidia/ARDY-G1-RP-25FPS-Horizon8 |
| OpenCodeReasoning-Nemotron-1.1-32B | original | bf16 | | 138 | Qwen/Qwen2.5-32B-Instruct |
| Audio2Emotion-v2.2 | original | bf16 | | 138 | nvidia/Audio2Emotion-v2.2 |
| Qwen3-Nemotron-32B-RLBFF | original | bf16 | | 138 | Qwen/Qwen3-32B |
| geneformer_V2_316M | original | bf16 | | 137 | nvidia/geneformer_V2_316M |
| NV-Proteina-Complexa-Protein-Target-160M-v1 | original | bf16 | | 137 | nvidia/NV-Proteina-Complexa-Protein-Target-160M-v1 |
| Nemotron-Flash-3B | original | bf16 | | 135 | nvidia/Nemotron-Flash-3B |
| nemotron-ocr-v1 | original | bf16 | | 135 | nvidia/nemotron-ocr-v1 |
| stt_uz_fastconformer_hybrid_large_pc | original | bf16 | | 134 | nvidia/stt_uz_fastconformer_hybrid_large_pc |
| Cosmos-0.1-Tokenizer-CI16x16 | original | bf16 | | 134 | nvidia/Cosmos-0.1-Tokenizer-CI16x16 |
| OpenMath-Mistral-7B-v0.1-hf | original | bf16 | | 133 | mistralai/Mistral-7B-v0.1 |
| Llama3-ChatQA-2-70B | original | bf16 | | 130 | nvidia/Llama3-ChatQA-2-70B |
| C-RADIOv2-VLM-H-RC3 | original | bf16 | | 130 | nvidia/C-RADIOv2-VLM-H-RC3 |
| MambaVision-L-21K | original | bf16 | | 129 | nvidia/MambaVision-L-21K |
| dlesym-v0-isccp-era5 | original | bf16 | | 129 | nvidia/dlesym-v0-isccp-era5 |
| OpenCodeReasoning-Nemotron-14B | original | bf16 | | 128 | Qwen/Qwen2.5-14B-Instruct |
| Cosmos-H-Surgical-Simulator | original | bf16 | | 128 | nvidia/Cosmos-Predict2.5-2B |
| tts_en_fastpitch | original | bf16 | | 126 | nvidia/tts_en_fastpitch |
| nemo-nano-codec-22khz-1.78kbps-12.5fps | original | bf16 | | 125 | nvidia/nemo-nano-codec-22khz-1.78kbps-12.5fps |
| Llama-3.1-Nemotron-Nano-VL-8B-V1-FP4-QAD | original | bf16 | | 125 | nvidia/Llama-3.1-Nemotron-Nano-VL-8B-V1-FP4-QAD |
| Efficient-DLM-8B | original | bf16 | | 122 | nvidia/Efficient-DLM-8B |
| Cosmos-Predict1-7B-Text2World-Sample-AV-Multiview | original | bf16 | | 121 | nvidia/Cosmos-Predict1-7B-Text2World-Sample-AV-Multiview |
| Cosmos-0.1-Tokenizer-CV4x8x8 | original | bf16 | | 120 | nvidia/Cosmos-0.1-Tokenizer-CV4x8x8 |
| AceMath-72B-RM | original | bf16 | | 119 | nvidia/AceMath-72B-RM |
| Mistral-NeMo-12B-Base | original | bf16 | | 117 | nvidia/Mistral-NeMo-12B-Base |
| Cosmos-H-Dreams | original | bf16 | | 116 | nvidia/Cosmos-Predict2.5-2B |
| Cosmos-1.0-Tokenizer-CV8x8x8 | original | bf16 | | 115 | nvidia/Cosmos-1.0-Tokenizer-CV8x8x8 |
| AceMath-72B-Instruct | original | bf16 | | 114 | nvidia/AceMath-72B-Instruct |
| Nemotron-H-47B-Reasoning-128K-FP8 | fp8 | fp8 | | 114 | nvidia/Nemotron-H-47B-Reasoning-128K |
| PixelDiT-1300M-1024px | original | bf16 | | 114 | nvidia/PixelDiT-1300M-1024px |
| Cosmos-0.1-Tokenizer-DV4x8x8 | original | bf16 | | 113 | nvidia/Cosmos-0.1-Tokenizer-DV4x8x8 |
| OpenMath-CodeLlama-70b-Python-hf | original | bf16 | | 112 | codellama/CodeLlama-70b-Python-hf |
| MambaVision-L3-512-21K | original | bf16 | | 112 | nvidia/MambaVision-L3-512-21K |
| NV-CodonFM-Encodon-TE-80M-v1 | original | bf16 | | 112 | nvidia/NV-CodonFM-Encodon-TE-80M-v1 |
| GEM-X | original | bf16 | | 111 | nvidia/GEM-X |
| RADIO-B | original | bf16 | | 110 | nvidia/RADIO-B |
| Diffusion_Renderer_Forward_Cosmos_7B | original | bf16 | | 108 | nvidia/Diffusion_Renderer_Forward_Cosmos_7B |
| Qwen3-235B-A22B-Thinking-2507-Eagle3 | original | bf16 | | 106 | Qwen/Qwen3-235B-A22B-Thinking-2507 |
| VILA-HD-8B-PS3-1.5K-SigLIP | original | bf16 | | 104 | nvidia/VILA-HD-8B-PS3-1.5K-SigLIP |
| Llama-3_3-Nemotron-Super-49B-GenRM | original | bf16 | | 104 | nvidia/Llama-3_3-Nemotron-Super-49B-v1 |
| Nemotron-Research-GooseReason-4B-Instruct | original | bf16 | | 103 | Qwen/Qwen3-4B-Instruct-2507 |
| 4D-RGPT-8B | original | bf16 | | 103 | Efficient-Large-Model/NVILA-Lite-8B |
| AceMath-RL-Nemotron-7B | original | bf16 | | 102 | nvidia/AceMath-RL-Nemotron-7B |
| VILA-HD-8B-PS3-4K-SigLIP2 | original | bf16 | | 102 | nvidia/VILA-HD-8B-PS3-4K-SigLIP2 |
| Llama-3.3-Nemotron-70B-Reward | original | bf16 | | 101 | meta-llama/Llama-3.3-70B-Instruct |
| Qwen3-Nemotron-235B-A22B-GenRM | original | bf16 | | 100 | Qwen/Qwen3-235B-A22B-Thinking-2507 |
| Cosmos-1.0-Prompt-Upsampler-12B-Text2World | original | bf16 | | 99 | nvidia/Cosmos-1.0-Prompt-Upsampler-12B-Text2World |
| Cosmos-Tokenize1-CI8x8-360p | original | bf16 | | 99 | nvidia/Cosmos-Tokenize1-CI8x8-360p |
| VILA-HD-8B-PS3-4K-SigLIP | original | bf16 | | 99 | nvidia/VILA-HD-8B-PS3-4K-SigLIP |
| GR00T-N1.6-BEHAVIOR1k | original | bf16 | | 99 | nvidia/GR00T-N1.6-3B |
| OpenCodeReasoning-Nemotron-1.1-7B | original | bf16 | | 98 | Qwen/Qwen2.5-7B-Instruct |
| Llama-3.3-Nemotron-70B-Select | original | bf16 | | 97 | meta-llama/Llama-3.3-70B-Instruct |
| Kimodo-G1-SEED-v1 | original | bf16 | | 97 | nvidia/Kimodo-G1-SEED-v1 |
| RADIO-H | original | bf16 | | 95 | nvidia/RADIO-H |
| KVzap-linear-Qwen3-8B | original | bf16 | | 92 | nvidia/KVzap-linear-Qwen3-8B |
| Cosmos-Predict1-4B | original | bf16 | | 91 | nvidia/Cosmos-Predict1-4B |
| Cosmos-Tokenize1-DV4x8x8-360p | original | bf16 | | 91 | nvidia/Cosmos-Tokenize1-DV4x8x8-360p |
| Cosmos-Predict1-7B-Decoder-DV8x16x16ToCV8x8x8-720p | original | bf16 | | 91 | nvidia/Cosmos-Predict1-7B-Decoder-DV8x16x16ToCV8x8x8-720p |
| Liver_Scan_Gr00t_Cosmos_Rel | original | bf16 | | 91 | nvidia/Liver_Scan_Gr00t_Cosmos_Rel |
| NV-La-Proteina-Motif-v1 | original | bf16 | | 91 | nvidia/NV-La-Proteina-Motif-v1 |
| esm2_t12_35M_UR50D | original | bf16 | | 90 | nvidia/esm2_t12_35M_UR50D |
| Cosmos-Tokenize1-CV4x8x8-360p | original | bf16 | | 89 | nvidia/Cosmos-Tokenize1-CV4x8x8-360p |
| domino_drivaerml | original | bf16 | | 89 | nvidia/domino_drivaerml |
| stt_nl_fastconformer_hybrid_large_pc | original | bf16 | | 89 | nvidia/stt_nl_fastconformer_hybrid_large_pc |
| groupvit-gcc-redcaps | original | bf16 | | 88 | nvidia/groupvit-gcc-redcaps |
| VILA-HD-8B-PS3-1.5K-C-RADIOv2 | original | bf16 | | 88 | nvidia/VILA-HD-8B-PS3-1.5K-C-RADIOv2 |
| OpenMath2-Llama3.1-70B | original | bf16 | | 86 | meta-llama/Llama-3.1-70B |
| Qwen-2.5-Nemotron-32B-Reward | original | bf16 | | 85 | Qwen/Qwen2.5-32B-Instruct |
| VILA-HD-8B-PS3-4K-C-RADIOv2 | original | bf16 | | 85 | nvidia/VILA-HD-8B-PS3-4K-C-RADIOv2 |
| DLER-R1-7B-Research | original | bf16 | | 85 | deepseek-ai/DeepSeek-R1-Distill-Qwen-7B |
| Cosmos-0.1-Tokenizer-CV8x8x8 | original | bf16 | | 84 | nvidia/Cosmos-0.1-Tokenizer-CV8x8x8 |
| transolver_drivaerml | original | bf16 | | 84 | nvidia/transolver_drivaerml |
| Llama-3_1-Nemotron-Ultra-253B-CPT-v1 | original | bf16 | | 83 | nvidia/Llama-3_1-Nemotron-Ultra-253B-CPT-v1 |
| Llama-3.1-Nemotron-8B-UltraLong-2M-Instruct | original | bf16 | | 82 | nvidia/Llama-3.1-Nemotron-8B-UltraLong-2M-Instruct |
| C-RADIOv2-VLM-H | original | bf16 | | 82 | nvidia/C-RADIOv2-VLM-H |
| DreamDojo | original | bf16 | | 82 | nvidia/DreamDojo |
| TMR-SOMA-RP-v1 | original | bf16 | | 81 | nvidia/TMR-SOMA-RP-v1 |
| SteerLM-llama2-13B | original | bf16 | | 79 | nvidia/SteerLM-llama2-13B |
| audio-flamingo-3-chat | original | bf16 | | 79 | nvidia/audio-flamingo-3 |
| figconvnet_drivaerml_surface | original | bf16 | | 79 | nvidia/figconvnet_drivaerml_surface |
| Ising-Calibration-1.5-31B-NVFP4 | nvfp4 | nvfp4 | | 79 | google/gemma-4-31b |
| AceInstruct-72B | original | bf16 | | 78 | nvidia/AceInstruct-72B |
| Cosmos-Tokenizer-CI8x8-Lidar | original | bf16 | | 78 | nvidia/Cosmos-Tokenizer-CI8x8-Lidar |
| Ising-Calibration-1.5-31B-BF16 | original | bf16 | | 78 | google/gemma-4-31b |
| OpenMath-Nemotron-14B-Kaggle | original | bf16 | | 77 | Qwen/Qwen2.5-14B |
| NV-Proteina-200M-v1 | original | bf16 | | 77 | nvidia/NV-Proteina-200M-v1 |
| stt_ua_fastconformer_hybrid_large_pc | original | bf16 | | 77 | nvidia/stt_ua_fastconformer_hybrid_large_pc |
| CWIP-1.0 | original | bf16 | | 76 | nvidia/CWIP-1.0 |
| stt_be_fastconformer_hybrid_large_pc | original | bf16 | | 75 | nvidia/stt_be_fastconformer_hybrid_large_pc |
| GR00T-N1-2B-tuned-Nut-Pouring-task | original | bf16 | | 75 | nvidia/GR00T-N1-2B |
| UniRelight | original | bf16 | | 75 | nvidia/UniRelight |
| MambaVision-L2-1K | original | bf16 | | 74 | nvidia/MambaVision-L2-1K |
| ChronoEdit-14B-Diffusers | original | bf16 | | 74 | nvidia/ChronoEdit-14B-Diffusers |
| xmgn_drivaerml_surface | original | bf16 | | 74 | nvidia/xmgn_drivaerml_surface |
| Cosmos-0.1-Tokenizer-DV8x8x8 | original | bf16 | | 73 | nvidia/Cosmos-0.1-Tokenizer-DV8x8x8 |
| OpenCodeReasoning-Nemotron-1.1-14B | original | bf16 | | 73 | Qwen/Qwen2.5-14B-Instruct |
| Qwen3-235B-A22B-Thinking-2507-FP4-Eagle3 | original | bf16 | | 73 | Qwen/Qwen3-235B-A22B-Thinking-2507-FP4 |
| Ising-Decoder-SurfaceCode-1-Accurate | original | bf16 | | 73 | nvidia/Ising-Decoder-SurfaceCode-1-Accurate |
| NFT-32B | original | bf16 | | 72 | Qwen/Qwen2.5-32B |
| stt_en_citrinet_256_ls | original | bf16 | | 72 | nvidia/stt_en_citrinet_256_ls |
| MambaVision-L-1K | original | bf16 | | 71 | nvidia/MambaVision-L-1K |
| Qwen3-30B-A3B-Thinking-2507-Eagle3 | original | bf16 | | 71 | Qwen/Qwen3-30-A3B-Thinking-2507 |
| Llama-3.1-Nemotron-70B-Instruct | original | bf16 | | 70 | meta-llama/Llama-3.1-70B-Instruct |
| Cosmos-0.1-Tokenizer-CV8x16x16 | original | bf16 | | 70 | nvidia/Cosmos-0.1-Tokenizer-CV8x16x16 |
| cbottle | original | bf16 | | 70 | nvidia/cbottle |
| NV-GenMol-89M-v2 | original | bf16 | | 69 | nvidia/NV-GenMol-89M-v2 |
| Qwen-3-Nemotron-32B-Reward | original | bf16 | | 68 | Qwen/Qwen3-32B |
| NV-CodonFM-Encodon-Cdwt-1B-v1 | original | bf16 | | 68 | nvidia/NV-CodonFM-Encodon-Cdwt-1B-v1 |
| Cosmos-Transfer-LidarGen | original | bf16 | | 68 | nvidia/Cosmos-Transfer-LidarGen |
| NV-CodonFM-Encodon-80M-v1 | original | bf16 | | 68 | nvidia/NV-CodonFM-Encodon-80M-v1 |
| Cosmos-Tokenizer-Surg | original | bf16 | | 68 | nvidia/Cosmos-Tokenizer-Surg |
| healda | original | bf16 | | 68 | nvidia/healda |
| NV-Proteina-Complexa-AME-160M-v1 | original | bf16 | | 68 | nvidia/NV-Proteina-Complexa-AME-160M-v1 |
| Kimodo-SOMA-SEED-v1 | original | bf16 | | 68 | nvidia/Kimodo-SOMA-SEED-v1 |
| NFT-7B | original | bf16 | | 67 | Qwen/Qwen2.5-Math-7B |
| Kimi-K2-Thinking-Eagle3 | original | bf16 | | 66 | moonshotai/Kimi-K2-Thinking |
| NeKo-v0-post-correction | original | bf16 | | 65 | nvidia/NeKo-v0-post-correction |
| Cosmos-Tokenize1-CI16x16-360p | original | bf16 | | 65 | nvidia/Cosmos-Tokenize1-CI16x16-360p |
| Cosmos-Tokenize1-DI8x8-360p | original | bf16 | | 65 | nvidia/Cosmos-Tokenize1-DI8x8-360p |
| PS3-1.5K-SigLIP2 | original | bf16 | | 65 | google/siglip2-so400m-patch14-384 |
| DLER-Llama-Nemotron-8B-Merge-Research | merge | merge | | 65 | nvidia/Llama-3.1-Nemotron-Nano-8B-v1 |
| Cosmos-0.1-Tokenizer-DV8x16x16 | original | bf16 | | 64 | nvidia/Cosmos-0.1-Tokenizer-DV8x16x16 |
| NemoGuard-JailbreakDetect | original | bf16 | | 64 | nvidia/NemoGuard-JailbreakDetect |
| Cosmos-Tokenize1-DI16x16-360p | original | bf16 | | 64 | nvidia/Cosmos-Tokenize1-DI16x16-360p |
| Llama-3.3-Nemotron-70B-Feedback | original | bf16 | | 64 | meta-llama/Llama-3.3-70B-Instruct |
| SO_ARM_Starter_Gr00t | original | bf16 | | 64 | nvidia/SO_ARM_Starter_Gr00t |
| stt_ru_conformer_ctc_large | original | bf16 | | 64 | nvidia/stt_ru_conformer_ctc_large |
| audio-codec-44khz | original | bf16 | | 63 | nvidia/audio-codec-44khz |
| dragon-multiturn-query-encoder | original | bf16 | | 62 | nvidia/dragon-multiturn-query-encoder |
| dragon-multiturn-context-encoder | original | bf16 | | 62 | nvidia/dragon-multiturn-context-encoder |
| AnyFlow-Wan2.1-T2V-1.3B-Diffusers | original | bf16 | | 61 | Wan-AI/Wan2.1-T2V-1.3B-Diffusers |
| MambaVision-L2-512-21K | original | bf16 | | 60 | nvidia/MambaVision-L2-512-21K |
| esm2_t30_150M_UR50D | original | bf16 | | 60 | nvidia/esm2_t30_150M_UR50D |
| NV-CodonFM-Encodon-600M-v1 | original | bf16 | | 60 | nvidia/NV-CodonFM-Encodon-600M-v1 |
| RADIOv2-bigG | original | bf16 | | 59 | nvidia/RADIOv2-bigG |
| corrdiff-cmip6-era5 | original | bf16 | | 59 | nvidia/corrdiff-cmip6-era5 |
| Cosmos-Predict2-2B-Sample-Action-Conditioned | original | bf16 | | 58 | nvidia/Cosmos-Predict2-2B-Sample-Action-Conditioned |
| ChronoEdit-14B-Diffusers-Upscaler-Lora | lora | lora | | 58 | nvidia/ChronoEdit-14B-Diffusers |
| dlesym-v1-era5 | original | bf16 | | 58 | nvidia/dlesym-v1-era5 |
| E-RADIO | original | bf16 | | 57 | nvidia/E-RADIO |
| audio-codec-22khz | original | bf16 | | 57 | nvidia/audio-codec-22khz |
| Cosmos-Predict1-13B-Video2World | original | bf16 | | 57 | nvidia/Cosmos-Predict1-13B-Video2World |
| stt_ru_conformer_transducer_large | original | bf16 | | 56 | nvidia/stt_ru_conformer_transducer_large |
| stt_pt_fastconformer_hybrid_large_pc | original | bf16 | | 56 | nvidia/stt_pt_fastconformer_hybrid_large_pc |
| esm2_t36_3B_UR50D | original | bf16 | | 56 | nvidia/esm2_t36_3B_UR50D |
| Cosmos-Policy-ALOHA-Predict2-2B | original | bf16 | | 56 | nvidia/Cosmos-Predict2-2B-Video2World |
| Llama-3.3-Nemotron-70B-Edit | original | bf16 | | 55 | meta-llama/Llama-3.3-70B-Instruct |
| OpenCodeReasoning-Nemotron-32B-IOI | original | bf16 | | 55 | Qwen/Qwen2.5-32B-Instruct |
| KVzap-linear-Llama-3.1-8B-Instruct | original | bf16 | | 55 | nvidia/KVzap-linear-Llama-3.1-8B-Instruct |
| OpenMath-CodeLlama-13b-Python-hf | original | bf16 | | 54 | codellama/CodeLlama-13b-Python-hf |
| Llama-3_3-Nemotron-Super-49B-GenRM-Multilingual | original | bf16 | | 54 | nvidia/Llama-3_3-Nemotron-Super-49B-v1 |
| GN1x-Tuned-Arena-GR1-Manipulation | original | bf16 | | 54 | nvidia/GN1x-Tuned-Arena-GR1-Manipulation |
| nemo-megatron-gpt-5B | original | bf16 | | 53 | nvidia/nemo-megatron-gpt-5B |
| NV-Megalodon-GEOM-Drugs-v1 | original | bf16 | | 53 | nvidia/NV-Megalodon-GEOM-Drugs-v1 |
| stt_hr_conformer_transducer_large | original | bf16 | | 52 | nvidia/stt_hr_conformer_transducer_large |
| Qwen3-Nemotron-14B-BRRM | original | bf16 | | 51 | Qwen/Qwen3-14B |
| GR00T-N1.5-3B_Assemble_Trocar | original | bf16 | | 51 | nvidia/GR00T-N1.5-3B_Assemble_Trocar |
| stt_fr_conformer_ctc_large | original | bf16 | | 51 | nvidia/stt_fr_conformer_ctc_large |
| Llama-3.1-8B-Medusa-FP8 | fp8 | fp8 | | 50 | — |
| NV-CodonFM-Encodon-1B-v1 | original | bf16 | | 50 | nvidia/NV-CodonFM-Encodon-1B-v1 |
| KVzap-mlp-Qwen3-32B | original | bf16 | | 50 | nvidia/KVzap-mlp-Qwen3-32B |
| nemo-megatron-t5-3B | original | bf16 | | 49 | nvidia/nemo-megatron-t5-3B |
| stt_de_conformer_transducer_large | original | bf16 | | 46 | nvidia/stt_de_conformer_transducer_large |
| stt_zh_conformer_transducer_large | original | bf16 | | 44 | nvidia/stt_zh_conformer_transducer_large |
| stt_de_conformer_ctc_large | original | bf16 | | 36 | nvidia/stt_de_conformer_ctc_large |
| stt_en_fastconformer_transducer_xlarge | original | bf16 | | 36 | nvidia/stt_en_fastconformer_transducer_xlarge |
| stt_fr_conformer_transducer_large | original | bf16 | | 26 | nvidia/stt_fr_conformer_transducer_large |
| stt_zh_citrinet_1024_gamma_0_25 | original | bf16 | | 23 | nvidia/stt_zh_citrinet_1024_gamma_0_25 |
| stt_be_conformer_transducer_large | original | bf16 | | 18 | nvidia/stt_be_conformer_transducer_large |
| stt_en_fastconformer_transducer_xxlarge | original | bf16 | | 13 | nvidia/stt_en_fastconformer_transducer_xxlarge |