HF Model & Benchmark Matrix

24,078 variants · 14,984 scores · 120 benchmarks
Home/Orgs/lmstudio-community

lmstudio-community

quantizer · 658 variants · 0 roots

huggingface
https://huggingface.co/lmstudio-community

Top variants (658)

variantkindquantvRAMdlroot
gemma-4-E4B-it-MLX-4bitmlxmlx1,326,860google/gemma-4-E4B-it
gemma-4-E4B-it-MLX-5bitmlxmlx1,279,787google/gemma-4-E4B-it
gemma-4-E4B-it-MLX-8bitmlxmlx1,279,665google/gemma-4-E4B-it
gemma-4-E4B-it-MLX-6bitmlxmlx1,274,997google/gemma-4-E4B-it
Qwen3.6-27B-MLX-8bitmlxmlx1,025,409Qwen/Qwen3.6-27B
gemma-4-26B-A4B-it-QAT-MLX-4bitmlxmlx994,988google/gemma-4-26B-A4B-it-QAT
Qwen3.6-27B-MLX-4bitmlxmlx973,375Qwen/Qwen3.6-27B
Qwen3.6-27B-MLX-6bitmlxmlx942,405Qwen/Qwen3.6-27B
Qwen3.6-27B-MLX-5bitmlxmlx923,303Qwen/Qwen3.6-27B
gemma-4-E4B-it-GGUFggufgguf736,882google/gemma-4-E4B-it
Qwen3.5-9B-MLX-4bitmlxmlx637,889Qwen/Qwen3.5-9B
Qwen3.5-9B-MLX-8bitmlxmlx604,308Qwen/Qwen3.5-9B
Qwen3.6-35B-A3B-MLX-4bitmlxmlx566,422Qwen/Qwen3.6-35B-A3B
gemma-4-12B-it-QAT-GGUFggufgguf561,871google/gemma-4-12B-it-qat-q4_0-unquantized
Qwen3.6-35B-A3B-MLX-8bitmlxmlx531,128Qwen/Qwen3.6-35B-A3B
Qwen3.6-35B-A3B-MLX-6bitmlxmlx527,346Qwen/Qwen3.6-35B-A3B
Qwen3.5-9B-GGUFggufgguf479,251Qwen/Qwen3.5-9B
Qwen3.6-27B-GGUFggufgguf422,088Qwen/Qwen3.6-27B
Qwen3.6-35B-A3B-GGUFggufgguf339,981Qwen/Qwen3.6-35B-A3B
DeepSeek-R1-0528-Qwen3-8B-MLX-4bitmlxmlx277,111deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
DeepSeek-R1-0528-Qwen3-8B-MLX-8bitmlxmlx254,746deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
gemma-4-26B-A4B-it-QAT-GGUFggufgguf251,678google/gemma-4-26B-A4B-it-qat-q4_0-unquantized
GLM-4.7-Flash-MLX-8bitmlxmlx245,863zai-org/GLM-4.7-Flash
gemma-4-31B-it-QAT-GGUFggufgguf231,878google/gemma-4-31B-it-qat-q4_0-unquantized
GLM-4.7-Flash-MLX-6bitmlxmlx221,213zai-org/GLM-4.7-Flash
gemma-4-12B-it-GGUFggufgguf199,683google/gemma-4-12B-it
gemma-4-E2B-it-MLX-4bitmlxmlx197,491google/gemma-4-E2B-it
gemma-4-E2B-it-MLX-8bitmlxmlx189,047google/gemma-4-E2B-it
gemma-4-E2B-it-MLX-6bitmlxmlx188,032google/gemma-4-E2B-it
gemma-4-E2B-it-MLX-5bitmlxmlx187,891google/gemma-4-E2B-it
Llama-3.2-3B-Instruct-GGUFggufgguf181,211meta-llama/Llama-3.2-3B-Instruct
gemma-4-26B-A4B-it-MLX-4bitmlxmlx162,593google/gemma-4-26B-A4B-it
Qwen3-Coder-Next-MLX-8bitmlxmlx161,488Qwen/Qwen3-Coder-Next
gemma-4-26B-A4B-it-MLX-8bitmlxmlx158,662google/gemma-4-26B-A4B-it
Qwen3-Coder-30B-A3B-Instruct-MLX-4bitmlxmlx158,079Qwen/Qwen3-Coder-30B-A3B-Instruct
gemma-4-26B-A4B-it-MLX-6bitmlxmlx154,772google/gemma-4-26B-A4B-it
gemma-4-26B-A4B-it-MLX-5bitmlxmlx153,889google/gemma-4-26B-A4B-it
Qwen3-Coder-Next-MLX-4bitmlxmlx147,587Qwen/Qwen3-Coder-Next
Qwen3-Coder-30B-A3B-Instruct-MLX-8bitmlxmlx141,503Qwen/Qwen3-Coder-30B-A3B-Instruct
Qwen3-Coder-Next-MLX-6bitmlxmlx141,417Qwen/Qwen3-Coder-Next
Qwen3-Coder-30B-A3B-Instruct-MLX-5bitmlxmlx140,681Qwen/Qwen3-Coder-30B-A3B-Instruct
Qwen3-Coder-30B-A3B-Instruct-MLX-6bitmlxmlx138,724Qwen/Qwen3-Coder-30B-A3B-Instruct
gemma-4-E2B-it-GGUFggufgguf131,014google/gemma-4-E2B-it
Qwen2.5-Coder-14B-Instruct-MLX-4bitmlxmlx129,859Qwen/Qwen2.5-Coder-14B-Instruct
gpt-oss-20b-GGUFggufgguf111,963openai/gpt-oss-20b
GLM-4.6V-Flash-MLX-4bitmlxmlx108,490zai-org/GLM-4.6V-Flash
GLM-4.6V-Flash-MLX-8bitmlxmlx107,016zai-org/GLM-4.6V-Flash
GLM-4.6V-Flash-MLX-6bitmlxmlx106,027zai-org/GLM-4.6V-Flash
Qwen2.5-Coder-14B-Instruct-MLX-8bitmlxmlx104,469Qwen/Qwen2.5-Coder-14B-Instruct
gemma-4-31B-it-GGUFggufgguf104,397google/gemma-4-31B-it
Qwen3-VL-4B-Instruct-MLX-4bitmlxmlx103,396Qwen/Qwen3-VL-4B-Instruct
Qwen3-VL-4B-Instruct-MLX-8bitmlxmlx98,814Qwen/Qwen3-VL-4B-Instruct
Qwen3-VL-4B-Instruct-MLX-6bitmlxmlx98,301Qwen/Qwen3-VL-4B-Instruct
Qwen3-VL-4B-Instruct-MLX-5bitmlxmlx98,176Qwen/Qwen3-VL-4B-Instruct
Nemotron-3-Nano-Omni-30B-A3B-Reasoning-GGUFggufgguf95,554nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16
DeepSeek-R1-0528-Qwen3-8B-GGUFggufgguf95,307deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
Qwen3-VL-8B-Instruct-MLX-4bitmlxmlx93,137Qwen/Qwen3-VL-8B-Instruct
LFM2-24B-A2B-MLX-4bitmlxmlx88,854LiquidAI/LFM2-24B-A2B
LFM2-24B-A2B-MLX-8bitmlxmlx87,224LiquidAI/LFM2-24B-A2B
LFM2-24B-A2B-MLX-5bitmlxmlx86,999LiquidAI/LFM2-24B-A2B
LFM2.5-1.2B-Instruct-MLX-8bitmlxmlx86,728LiquidAI/LFM2.5-1.2B-Instruct
LFM2-24B-A2B-MLX-6bitmlxmlx86,701LiquidAI/LFM2-24B-A2B
LFM2.5-1.2B-Instruct-MLX-4bitmlxmlx85,465LiquidAI/LFM2.5-1.2B-Instruct
LFM2.5-1.2B-Instruct-MLX-6bitmlxmlx85,171LiquidAI/LFM2.5-1.2B-Instruct
Qwen3-VL-8B-Instruct-MLX-8bitmlxmlx78,640Qwen/Qwen3-VL-8B-Instruct
Qwen3-VL-8B-Instruct-MLX-5bitmlxmlx77,587Qwen/Qwen3-VL-8B-Instruct
Qwen3-VL-8B-Instruct-MLX-6bitmlxmlx77,430Qwen/Qwen3-VL-8B-Instruct
GLM-4.7-Flash-GGUFggufgguf73,664zai-org/GLM-4.7-Flash
Hermes-4-70B-MLX-4bitmlxmlx73,563NousResearch/Hermes-4-70B
Meta-Llama-3.1-8B-Instruct-GGUFggufgguf72,085meta-llama/Meta-Llama-3.1-8B-Instruct
Qwen2.5-Coder-14B-Instruct-GGUFggufgguf70,168Qwen/Qwen2.5-Coder-14B-Instruct
Qwen3-Coder-30B-A3B-Instruct-GGUFggufgguf69,847Qwen/Qwen3-Coder-30B-A3B-Instruct
Qwen3.5-4B-GGUFggufgguf69,212Qwen/Qwen3.5-4B
Qwen2.5-VL-7B-Instruct-GGUFggufgguf69,084Qwen/Qwen2.5-VL-7B-Instruct
Hermes-4-70B-MLX-8bitmlxmlx67,788NousResearch/Hermes-4-70B
Qwen3-VL-8B-Instruct-GGUFggufgguf67,315Qwen/Qwen3-VL-8B-Instruct
Hermes-4-70B-MLX-6bitmlxmlx67,142NousResearch/Hermes-4-70B
Qwen3-VL-4B-Instruct-GGUFggufgguf66,955Qwen/Qwen3-VL-4B-Instruct
Hermes-4-70B-MLX-5bitmlxmlx66,950NousResearch/Hermes-4-70B
Qwen3-Coder-Next-GGUFggufgguf63,685Qwen/Qwen3-Coder-Next
gemma-3-4b-it-GGUFggufgguf60,807google/gemma-3-4b-it
GLM-4.6V-Flash-GGUFggufgguf55,831zai-org/GLM-4.6V-Flash
Ministral-3-14B-Reasoning-2512-GGUFggufgguf55,624mistralai/Ministral-3-14B-Reasoning-2512
gemma-4-26B-A4B-it-GGUFggufgguf55,432google/gemma-4-26B-A4B-it
Qwen3-4B-Instruct-2507-MLX-4bitmlxmlx52,095Qwen/Qwen3-4B-Instruct-2507
Qwen3-4B-Thinking-2507-MLX-4bitmlxmlx51,394Qwen/Qwen3-4B-Thinking-2507
Qwen3-4B-Thinking-2507-MLX-8bitmlxmlx50,643Qwen/Qwen3-4B-Thinking-2507
gemma-3-1b-it-GGUFggufgguf50,530google/gemma-3-1b-it
Qwen3-4B-Thinking-2507-MLX-6bitmlxmlx50,306Qwen/Qwen3-4B-Thinking-2507
NVIDIA-Nemotron-3-Nano-30B-A3B-MLX-4bitmlxmlx49,487nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
Qwen3-4B-Instruct-2507-MLX-8bitmlxmlx47,737Qwen/Qwen3-4B-Instruct-2507
Phi-4-mini-reasoning-MLX-4bitmlxmlx47,298microsoft/Phi-4-mini-reasoning
Qwen3-4B-Instruct-2507-MLX-5bitmlxmlx47,154Qwen/Qwen3-4B-Instruct-2507
Qwen3-4B-Instruct-2507-MLX-6bitmlxmlx47,053Qwen/Qwen3-4B-Instruct-2507
Ministral-3-3B-Instruct-2512-GGUFggufgguf47,053mistralai/Ministral-3-3B-Instruct-2512-BF16
NVIDIA-Nemotron-3-Nano-4B-GGUFggufgguf46,371nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16
Qwen3-14B-GGUFggufgguf45,818Qwen/Qwen3-14B
Qwen3-14B-MLX-4bitmlxmlx45,562Qwen/Qwen3-14B
NVIDIA-Nemotron-3-Nano-30B-A3B-MLX-8bitmlxmlx45,024nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
NVIDIA-Nemotron-3-Nano-30B-A3B-MLX-6bitmlxmlx44,463nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
NVIDIA-Nemotron-3-Nano-30B-A3B-MLX-5bitmlxmlx44,375nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
Qwen3-VL-30B-A3B-Instruct-MLX-4bitmlxmlx40,797Qwen/Qwen3-VL-30B-A3B-Instruct
Qwen3-14B-MLX-8bitmlxmlx40,767Qwen/Qwen3-14B
Qwen2.5-Coder-32B-Instruct-MLX-4bitmlxmlx40,329Qwen/Qwen2.5-Coder-32B-Instruct
gpt-oss-120b-MLX-8bitmlxmlx39,723openai/gpt-oss-120b
gemma-3n-E4B-it-MLX-4bitmlxmlx39,259google/gemma-3n-E4B-it
gemma-3n-E4B-it-MLX-bf16mlxmlx39,156google/gemma-3n-E4B-it
gemma-3n-E4B-it-MLX-8bitmlxmlx38,565google/gemma-3n-E4B-it
gemma-3n-E4B-it-MLX-6bitmlxmlx38,425google/gemma-3n-E4B-it
Seed-OSS-36B-Instruct-MLX-8bitmlxmlx38,044ByteDance-Seed/Seed-OSS-36B-Instruct
Qwen2.5-Coder-32B-Instruct-MLX-8bitmlxmlx37,414Qwen/Qwen2.5-Coder-32B-Instruct
Seed-OSS-36B-Instruct-MLX-4bitmlxmlx33,856ByteDance-Seed/Seed-OSS-36B-Instruct
Seed-OSS-36B-Instruct-MLX-5bitmlxmlx33,616ByteDance-Seed/Seed-OSS-36B-Instruct
Seed-OSS-36B-Instruct-MLX-6bitmlxmlx33,590ByteDance-Seed/Seed-OSS-36B-Instruct
Devstral-Small-2-24B-Instruct-2512-GGUFggufgguf32,345mistralai/Devstral-Small-2-24B-Instruct-2512
gemma-4-12B-it-MLX-8bitmlxmlx30,686google/gemma-4-12B-it
Qwen3-VL-30B-A3B-Instruct-MLX-8bitmlxmlx29,898Qwen/Qwen3-VL-30B-A3B-Instruct
Olmo-3-32B-Think-MLX-4bitmlxmlx29,601allenai/Olmo-3-32B-Think
Olmo-3-32B-Think-MLX-8bitmlxmlx29,425allenai/Olmo-3-32B-Think
Qwen2.5-Coder-7B-Instruct-GGUFggufgguf29,417Qwen/Qwen2.5-Coder-7B-Instruct
Olmo-3-32B-Think-MLX-6bitmlxmlx29,392allenai/Olmo-3-32B-Think
Qwen3-VL-30B-A3B-Instruct-MLX-5bitmlxmlx29,317Qwen/Qwen3-VL-30B-A3B-Instruct
Qwen3-VL-30B-A3B-Instruct-MLX-6bitmlxmlx29,076Qwen/Qwen3-VL-30B-A3B-Instruct
Qwen3-8B-MLX-4bitmlxmlx28,941Qwen/Qwen3-8B
Qwen3.5-35B-A3B-GGUFggufgguf28,587Qwen/Qwen3.5-35B-A3B
QwQ-32B-MLX-4bitmlxmlx27,983Qwen/QwQ-32B
QwQ-32B-MLX-8bitmlxmlx27,916Qwen/QwQ-32B
Qwen3-8B-MLX-8bitmlxmlx27,769Qwen/Qwen3-8B
Qwen3.5-2B-GGUFggufgguf27,203Qwen/Qwen3.5-2B
Phi-4-reasoning-plus-MLX-4bitmlxmlx26,761microsoft/Phi-4-reasoning-plus
Qwen3-1.7B-MLX-8bitmlxmlx25,123Qwen/Qwen3-1.7B
Qwen3-1.7B-MLX-4bitmlxmlx24,682Qwen/Qwen3-1.7B
gpt-oss-120b-GGUFggufgguf24,510openai/gpt-oss-120b
Qwen3-30B-A3B-Instruct-2507-MLX-4bitmlxmlx24,478Qwen/Qwen3-30B-A3B-Instruct-2507
Qwen3-1.7B-MLX-bf16mlxmlx24,410Qwen/Qwen3-1.7B
Qwen3-8B-GGUFggufgguf24,231Qwen/Qwen3-8B
Mistral-Small-3.2-24B-Instruct-2506-MLX-6bitmlxmlx24,196mistralai/Mistral-Small-3.2-24B-Instruct-2506
Qwen2.5-7B-Instruct-GGUFggufgguf23,515Qwen/Qwen2.5-7B-Instruct
ERNIE-4.5-21B-A3B-MLX-4bitmlxmlx23,214baidu/ERNIE-4.5-21B-A3B-PT
ERNIE-4.5-21B-A3B-MLX-8bitmlxmlx23,069baidu/ERNIE-4.5-21B-A3B-PT
Qwen3-30B-A3B-Instruct-2507-MLX-8bitmlxmlx23,067Qwen/Qwen3-30B-A3B-Instruct-2507
ERNIE-4.5-21B-A3B-MLX-6bitmlxmlx22,981baidu/ERNIE-4.5-21B-A3B-PT
Qwen3-30B-A3B-Instruct-2507-MLX-6bitmlxmlx22,848Qwen/Qwen3-30B-A3B-Instruct-2507
Magistral-Small-2509-MLX-8bitmlxmlx22,565mistralai/Magistral-Small-2509
Magistral-Small-2509-MLX-4bitmlxmlx22,523mistralai/Magistral-Small-2509
Magistral-Small-2509-MLX-6bitmlxmlx21,930mistralai/Magistral-Small-2509
Magistral-Small-2509-MLX-5bitmlxmlx21,885mistralai/Magistral-Small-2509
DeepSeek-R1-Distill-Qwen-14B-GGUFggufgguf21,780deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
Qwen3-4B-Instruct-2507-GGUFggufgguf21,568Qwen/Qwen3-4B-Instruct-2507
Llama-3.3-70B-Instruct-GGUFggufgguf21,409meta-llama/Llama-3.3-70B-Instruct
MiniMax-M2.5-MLX-8bitmlxmlx20,793MiniMaxAI/MiniMax-M2.5
LFM2-1.2B-MLX-8bitmlxmlx20,771LiquidAI/LFM2-1.2B
LFM2-1.2B-MLX-bf16mlxmlx20,523LiquidAI/LFM2-1.2B
Mistral-Small-3.2-24B-Instruct-2506-MLX-4bitmlxmlx20,450mistralai/Mistral-Small-3.2-24B-Instruct-2506
Qwen3-4B-MLX-4bitmlxmlx19,896Qwen/Qwen3-4B
Mistral-Small-3.2-24B-Instruct-2506-MLX-8bitmlxmlx19,619mistralai/Mistral-Small-3.2-24B-Instruct-2506
olmOCR-2-7B-1025-GGUFggufgguf19,458allenai/olmOCR-2-7B-1025
Qwen3-4B-MLX-8bitmlxmlx19,174Qwen/Qwen3-4B
DeepSeek-Coder-V2-Lite-Instruct-GGUFggufgguf19,153deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct
Qwen2.5-7B-Instruct-1M-GGUFggufgguf18,631Qwen/Qwen2.5-7B-Instruct-1M
DeepSeek-R1-Distill-Qwen-7B-GGUFggufgguf18,348deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
Qwen3-1.7B-GGUFggufgguf18,314Qwen/Qwen3-1.7B
Qwen3-Next-80B-A3B-Instruct-MLX-4bitmlxmlx17,726Qwen/Qwen3-Next-80B-A3B-Instruct
LFM2.5-1.2B-Instruct-GGUFggufgguf17,600LiquidAI/LFM2.5-1.2B-Instruct
Qwen3-VL-30B-A3B-Instruct-GGUFggufgguf16,654Qwen/Qwen3-VL-30B-A3B-Instruct
Devstral-Small-2507-MLX-8bitmlxmlx16,570mistralai/Devstral-Small-2507
gemma-3-12b-it-GGUFggufgguf16,371google/gemma-3-12b-it
Hermes-4-70B-GGUFggufgguf16,329NousResearch/Hermes-4-70B
Qwen3-Next-80B-A3B-Instruct-MLX-8bitmlxmlx16,258Qwen/Qwen3-Next-80B-A3B-Instruct
gemma-4-31B-it-MLX-8bitmlxmlx16,137google/gemma-4-31B-it
Qwen3.5-0.8B-GGUFggufgguf16,054Qwen/Qwen3.5-0.8B
Qwen3-Next-80B-A3B-Instruct-MLX-6bitmlxmlx16,023Qwen/Qwen3-Next-80B-A3B-Instruct
Qwen3-Next-80B-A3B-Instruct-MLX-5bitmlxmlx15,938Qwen/Qwen3-Next-80B-A3B-Instruct
Devstral-Small-2507-MLX-4bitmlxmlx15,873mistralai/Devstral-Small-2507
Qwen2.5-Coder-7B-Instruct-MLX-4bitmlxmlx15,683Qwen/Qwen2.5-Coder-7B-Instruct
Devstral-Small-2507-MLX-6bitmlxmlx15,677mistralai/Devstral-Small-2507
Mistral-7B-Instruct-v0.3-GGUFggufgguf15,590mistralai/Mistral-7B-Instruct-v0.3
Devstral-Small-2507-MLX-bf16mlxmlx15,336mistralai/Devstral-Small-2507
Qwen2.5-VL-3B-Instruct-GGUFggufgguf15,317Qwen/Qwen2.5-VL-3B-Instruct
Qwen3-4B-Thinking-2507-GGUFggufgguf15,305Qwen/Qwen3-4B-Thinking-2507
DeepSeek-R1-Distill-Qwen-32B-GGUFggufgguf15,283deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
Qwen3-32B-MLX-4bitmlxmlx14,912Qwen/Qwen3-32B
Phi-4-mini-reasoning-GGUFggufgguf14,898microsoft/Phi-4-mini-reasoning
MiniMax-M2.5-MLX-4bitmlxmlx14,840MiniMaxAI/MiniMax-M2.5
phi-4-GGUFggufgguf14,719microsoft/phi-4
MiniMax-M2.5-MLX-6bitmlxmlx14,603MiniMaxAI/MiniMax-M2.5
Qwen3-32B-MLX-8bitmlxmlx14,477Qwen/Qwen3-32B
granite-4.0-h-tiny-GGUFggufgguf13,394ibm-granite/granite-4.0-h-tiny
Qwen2.5-Coder-32B-GGUFggufgguf13,126Qwen/Qwen2.5-Coder-32B
MiniMax-M2.7-GGUFggufgguf12,980MiniMaxAI/MiniMax-M2.7
Qwen3-4B-GGUFggufgguf12,591Qwen/Qwen3-4B
NVIDIA-Nemotron-3-Super-120B-A12B-GGUFggufgguf12,548nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16
Codestral-22B-v0.1-GGUFggufgguf12,360mistralai/Codestral-22B-v0.1
Mistral-Nemo-Instruct-2407-GGUFggufgguf12,118mistralai/Mistral-Nemo-Instruct-2407
Qwen3-32B-GGUFggufgguf11,443Qwen/Qwen3-32B
gemma-3-1B-it-qat-GGUFggufgguf11,373google/gemma-3-1b-it
LFM2-24B-A2B-GGUFggufgguf11,295LiquidAI/LFM2-24B-A2B
QwQ-32B-GGUFggufgguf11,202Qwen/QwQ-32B
Qwen2.5-14B-Instruct-1M-GGUFggufgguf10,867Qwen/Qwen2.5-14B-Instruct-1M
rnj-1-instruct-GGUFggufgguf10,828EssentialAI/rnj-1-instruct
gpt-oss-safeguard-20b-MLX-MXFP4mlxmlx10,513openai/gpt-oss-safeguard-20b
gemma-4-12B-it-MLX-6bitmlxmlx10,449google/gemma-4-12B-it
Qwen3-30B-A3B-MLX-4bitmlxmlx10,375Qwen/Qwen3-30B-A3B
Devstral-Small-2505-MLX-4bitmlxmlx10,251mistralai/Devstral-Small-2505
Qwen2.5-14B-Instruct-GGUFggufgguf10,063Qwen/Qwen2.5-14B-Instruct
Qwen3-30B-A3B-MLX-8bitmlxmlx10,014Qwen/Qwen3-30B-A3B
Qwen3-30B-A3B-Instruct-2507-GGUFggufgguf9,800Qwen/Qwen3-30B-A3B-Instruct-2507
Qwen3-0.6B-MLX-4bitmlxmlx9,745Qwen/Qwen3-0.6B
Meta-Llama-3-8B-Instruct-GGUFggufgguf9,462meta-llama/Meta-Llama-3-8B-Instruct
Qwen3.5-4B-MLX-4bitmlxmlx9,167Qwen/Qwen3.5-4B
Phi-4-reasoning-plus-GGUFggufgguf9,125microsoft/Phi-4-reasoning-plus
Qwen2.5-Coder-3B-Instruct-GGUFggufgguf9,065Qwen/Qwen2.5-Coder-3B-Instruct
gemma-4-12B-it-MLX-4bitmlxmlx9,013google/gemma-4-12B-it
Qwen3-0.6B-MLX-bf16mlxmlx8,710Qwen/Qwen3-0.6B
DeepSeek-R1-Distill-Llama-70B-GGUFggufgguf8,424deepseek-ai/DeepSeek-R1-Distill-Llama-70B
Qwen3-30B-A3B-GGUFggufgguf8,218Qwen/Qwen3-30B-A3B
Qwen3-Next-80B-A3B-Instruct-GGUFggufgguf8,155Qwen/Qwen3-Next-80B-A3B-Instruct
gemma-4-E4B-it-QAT-GGUFggufgguf8,103google/gemma-4-E4B-it-qat-q4_0-unquantized
gemma-2-9b-it-GGUFggufgguf8,050google/gemma-2-9b-it
Llama-3.2-1B-Instruct-GGUFggufgguf8,028meta-llama/Llama-3.2-1B-Instruct
Qwen2.5-VL-32B-Instruct-GGUFggufgguf7,903Qwen/Qwen2.5-VL-32B-Instruct
Qwen2.5-0.5B-Instruct-GGUFggufgguf7,851Qwen/Qwen2.5-0.5B-Instruct
NVIDIA-Nemotron-3-Nano-30B-A3B-GGUFggufgguf7,784nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
Mistral-Small-3.2-24B-Instruct-2506-GGUFggufgguf7,750mistralai/Mistral-Small-3.2-24B-Instruct-2506
Magistral-Small-2506-MLX-4bitmlxmlx7,553mistralai/Magistral-Small-2506
Qwen2.5-0.5B-Instruct-MLX-4bitmlxmlx7,438Qwen/Qwen2.5-0.5B-Instruct
magistral-small-2506-mlx-bf16mlxmlx7,423mistralai/Magistral-Small-2506
gemma-3n-E4B-it-text-GGUFggufgguf7,193google/gemma-3n-E4B
Qwen2.5-VL-72B-Instruct-GGUFggufgguf7,038Qwen/Qwen2.5-VL-72B-Instruct
Qwen2.5-Coder-1.5B-Instruct-GGUFggufgguf7,020Qwen/Qwen2.5-Coder-1.5B-Instruct
DeepSeek-R1-Distill-Llama-8B-GGUFggufgguf7,009deepseek-ai/DeepSeek-R1-Distill-Llama-8B
Seed-OSS-36B-Instruct-GGUFggufgguf6,828ByteDance-Seed/Seed-OSS-36B-Instruct
DeepSeek-R1-Distill-Qwen-1.5B-GGUFggufgguf6,734deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
Qwen2.5-32B-Instruct-GGUFggufgguf6,558Qwen/Qwen2.5-32B-Instruct
MiniMax-M2-MLX-4bitmlxmlx6,398MiniMaxAI/MiniMax-M2
MiniMax-M2-MLX-8bitmlxmlx6,378MiniMaxAI/MiniMax-M2
MiniMax-M2-MLX-6bitmlxmlx6,247MiniMaxAI/MiniMax-M2
granite-4.1-8b-GGUFggufgguf6,222ibm-granite/granite-4.1-8b
gemma-3-27b-it-GGUFggufgguf6,199google/gemma-3-27b-it
dolphin-2.8-mistral-7b-v02-GGUFggufgguf6,164alpindale/Mistral-7B-v0.2-hf
gemma-4-E2B-it-QAT-GGUFggufgguf6,162google/gemma-4-E2B-it-qat-q4_0-unquantized
gemma-2-2b-it-GGUFggufgguf5,960google/gemma-2-2b-it
Magistral-Small-2509-GGUFggufgguf5,867mistralai/Magistral-Small-2509
DeepSeek-R1-GGUFggufgguf5,842deepseek-ai/DeepSeek-R1
Qwen2.5-Coder-1.5B-Instruct-MLX-8bitmlxmlx5,727Qwen/Qwen2.5-Coder-1.5B-Instruct
Qwen2.5-Coder-32B-Instruct-GGUFggufgguf5,578Qwen/Qwen2.5-Coder-32B-Instruct
gemma-3-27B-it-qat-GGUFggufgguf5,526google/gemma-3-27b-it
Qwen3-VL-32B-Instruct-GGUFggufgguf5,452Qwen/Qwen3-VL-32B-Instruct
Qwen2.5-3B-Instruct-GGUFggufgguf5,401Qwen/Qwen2.5-3B-Instruct
gemma-4-31B-it-MLX-4bitmlxmlx5,389google/gemma-4-31B-it
Qwen3.5-27B-GGUFggufgguf5,334Qwen/Qwen3.5-27B
Qwen3.5-122B-A10B-GGUFggufgguf5,309Qwen/Qwen3.5-122B-A10B
Qwen3-Coder-480B-A35B-Instruct-MLX-6bitmlxmlx5,241Qwen/Qwen3-Coder-480B-A35B-Instruct
gpt-oss-safeguard-120b-MLX-MXFP4mlxmlx4,973openai/gpt-oss-safeguard-120b
Qwen3.5-397B-A17B-MLX-8bitmlxmlx4,852Qwen/Qwen3.5-397B-A17B
Olmo-3-32B-Think-GGUFggufgguf4,825allenai/Olmo-3-32B-Think
Qwen2.5-Coder-7B-Instruct-MLX-8bitmlxmlx4,793Qwen/Qwen2.5-Coder-7B-Instruct
Qwen3-Coder-480B-A35B-Instruct-MLX-4bitmlxmlx4,734Qwen/Qwen3-Coder-480B-A35B-Instruct
Devstral-Small-2507-GGUFggufgguf4,590mistralai/Devstral-Small-2507
Qwen3-Coder-480B-A35B-Instruct-MLX-8bitmlxmlx4,564Qwen/Qwen3-Coder-480B-A35B-Instruct
SmolLM2-1.7B-Instruct-GGUFggufgguf4,402HuggingFaceTB/SmolLM2-1.7B-Instruct
granite-4.1-30b-GGUFggufgguf4,364ibm-granite/granite-4.1-30b
granite-3.2-8b-instruct-GGUFggufgguf4,318ibm-granite/granite-3.2-8b-instruct
KAT-Dev-MLX-8bitmlxmlx4,234Kwaipilot/KAT-Dev
Qwen2.5-1.5B-Instruct-GGUFggufgguf4,141Qwen/Qwen2.5-1.5B-Instruct
Qwen2.5-Coder-3B-GGUFggufgguf4,078Qwen/Qwen2.5-Coder-3B
ERNIE-4.5-21B-A3B-PT-GGUFggufgguf4,066baidu/ERNIE-4.5-21B-A3B-PT
Qwen2.5-Coder-3B-Instruct-MLX-4bitmlxmlx4,058Qwen/Qwen2.5-Coder-3B-Instruct
GLM-4.7-Flash-MLX-4bitmlxmlx3,945zai-org/GLM-4.7-Flash
Qwen3-0.6B-GGUFggufgguf3,823Qwen/Qwen3-0.6B
granite-4.0-h-small-MLX-8bitmlxmlx3,669ibm-granite/granite-4.0-h-small
Qwen3.5-4B-MLX-8bitmlxmlx3,617Qwen/Qwen3.5-4B
Phi-4-mini-instruct-GGUFggufgguf3,601microsoft/Phi-4-mini-instruct
EXAONE-3.5-7.8B-Instruct-GGUFggufgguf3,583LGAI-EXAONE/EXAONE-3.5-7.8B-Instruct
granite-4.1-3b-GGUFggufgguf3,540ibm-granite/granite-4.1-3b
Qwen3-235B-A22B-Instruct-2507-MLX-4bitmlxmlx3,496Qwen/Qwen3-235B-A22B-Instruct-2507
Qwen3-VL-32B-Thinking-MLX-8bitmlxmlx3,489Qwen/Qwen3-VL-32B-Thinking
Ministral-3-8B-Reasoning-2512-GGUFggufgguf3,487mistralai/Ministral-3-8B-Reasoning-2512
Yi-Coder-1.5B-GGUFggufgguf3,41001-ai/Yi-Coder-1.5B
Qwen3.5-2B-MLX-8bitmlxmlx3,382Qwen/Qwen3.5-2B
AMD-OLMo-1B-SFT-DPO-GGUFggufgguf3,294amd/AMD-OLMo-1B-SFT-DPO
medgemma-27b-text-it-MLX-4bitmlxmlx3,290google/medgemma-27b-text-it
NuExtract-v1.5-GGUFggufgguf3,280numind/NuExtract-v1.5
EXAONE-3.5-2.4B-Instruct-GGUFggufgguf3,272LGAI-EXAONE/EXAONE-3.5-2.4B-Instruct
Qwen3-235B-A22B-Instruct-2507-MLX-8bitmlxmlx3,261Qwen/Qwen3-235B-A22B-Instruct-2507
OpenCoder-1.5B-Instruct-GGUFggufgguf3,249infly/OpenCoder-1.5B-Instruct
Qwen3-235B-A22B-Instruct-2507-MLX-6bitmlxmlx3,232Qwen/Qwen3-235B-A22B-Instruct-2507
Qwen3.5-0.8B-MLX-8bitmlxmlx3,227Qwen/Qwen3.5-0.8B
Llama-3.1-Tulu-3-8B-GGUFggufgguf3,226allenai/Llama-3.1-Tulu-3-8B
Ministral-3-8B-Instruct-2512-GGUFggufgguf3,100mistralai/Ministral-3-8B-Instruct-2512-BF16
gemma-2-27b-it-GGUFggufgguf3,071google/gemma-2-27b-it
gpt-oss-20b-MLX-8bitmlxmlx3,027openai/gpt-oss-20b
Hermes-4-405B-MLX-5bitmlxmlx2,955NousResearch/Hermes-4-405B
Qwen3-VL-8B-Thinking-GGUFggufgguf2,952Qwen/Qwen3-VL-8B-Thinking
Qwen2.5-Coder-14B-GGUFggufgguf2,942Qwen/Qwen2.5-Coder-14B
gemma-4-31B-it-MLX-6bitmlxmlx2,915google/gemma-4-31B-it
embeddinggemma-300m-qat-GGUFggufgguf2,877google/embeddinggemma-300M-qat-q4_0-unquantized
Ministral-3-14B-Instruct-2512-GGUFggufgguf2,838mistralai/Ministral-3-14B-Instruct-2512-BF16
Ministral-3-3B-Reasoning-2512-GGUFggufgguf2,816mistralai/Ministral-3-3B-Reasoning-2512
Qwen3-Coder-480B-A35B-Instruct-GGUFggufgguf2,767Qwen/Qwen3-Coder-480B-A35B-Instruct
OREAL-DeepSeek-R1-Distill-Qwen-7B-GGUFggufgguf2,729internlm/OREAL-DeepSeek-R1-Distill-Qwen-7B
Qwen2.5-14B-Instruct-MLX-4bitmlxmlx2,725Qwen/Qwen2.5-14B-Instruct
granite-3.1-8b-instruct-GGUFggufgguf2,603ibm-granite/granite-3.1-8b-instruct
Qwen3-235B-A22B-Instruct-2507-GGUFggufgguf2,539Qwen/Qwen3-235B-A22B-Instruct-2507
deepseek-coder-6.7B-kexer-GGUFggufgguf2,506JetBrains/deepseek-coder-6.7B-kexer
Llama-4-Scout-17B-16E-MLX-text-8bitmlxmlx2,444meta-llama/Llama-4-Scout-17B-16E-Instruct
Qwen3.5-2B-MLX-4bitmlxmlx2,413Qwen/Qwen3.5-2B
Laguna-S-2.1-GGUFggufgguf2,406poolside/Laguna-S-2.1
DeepSeek-Coder-V2-Instruct-0724-GGUFggufgguf2,306deepseek-ai/DeepSeek-Coder-V2-Instruct-0724
gemma-3-270m-it-MLX-8bitmlxmlx2,290google/gemma-3-270m-it
Phi-3.1-mini-4k-instruct-GGUFggufgguf2,285microsoft/Phi-3-mini-4k-instruct
Qwen2.5-7B-Instruct-MLX-4bitmlxmlx2,245Qwen/Qwen2.5-7B-Instruct
Qwen2.5-Coder-1.5B-Instruct-MLX-4bitmlxmlx2,240Qwen/Qwen2.5-Coder-1.5B-Instruct
gemma-4-12B-it-MLX-5bitmlxmlx2,234google/gemma-4-12B-it
Qwen2-VL-7B-Instruct-GGUFggufgguf2,210Qwen/Qwen2-VL-7B-Instruct
Mistral-Small-3.1-24B-Instruct-2503-GGUFggufgguf2,160mistralai/Mistral-Small-3.1-24B-Instruct-2503
Qwen3-VL-30B-A3B-Thinking-GGUFggufgguf2,150Qwen/Qwen3-VL-30B-A3B-Thinking
Magistral-Small-2506-GGUFggufgguf2,136mistralai/Magistral-Small-2506
Devstral-Small-2505-GGUFggufgguf2,088mistralai/Devstral-Small-2505
pixtral-12b-GGUFggufgguf2,072mistral-community/pixtral-12b
Qwen2.5-Coder-0.5B-Instruct-GGUFggufgguf2,025Qwen/Qwen2.5-Coder-0.5B-Instruct
GLM-4.5-Air-MLX-8bitmlxmlx1,997zai-org/GLM-4.5-Air
MiniMax-M2.5-GGUFggufgguf1,970MiniMaxAI/MiniMax-M2.5
Qwen3-VL-32B-Thinking-GGUFggufgguf1,898Qwen/Qwen3-VL-32B-Thinking
Qwen3-VL-2B-Instruct-GGUFggufgguf1,894Qwen/Qwen3-VL-2B-Instruct
Qwen3.5-0.8B-MLX-4bitmlxmlx1,888Qwen/Qwen3.5-0.8B
LFM2.5-1.2B-Thinking-GGUFggufgguf1,865LiquidAI/LFM2.5-1.2B-Thinking
gemma-4-31B-it-MLX-5bitmlxmlx1,845google/gemma-4-31B-it
Llama-3.1-Nemotron-70B-Instruct-HF-GGUFggufgguf1,817nvidia/Llama-3.1-Nemotron-70B-Instruct-HF
MiniCPM-V-2_6-GGUFggufgguf1,815openbmb/MiniCPM-V-2_6
Laguna-XS-2.1-GGUFggufgguf1,790poolside/Laguna-XS-2.1
gemma-3n-E2B-it-text-GGUFggufgguf1,764google/gemma-3n-E2B
Phi-3.5-MoE-instruct-GGUFggufgguf1,732microsoft/Phi-3.5-MoE-instruct
MiniMax-M2-GGUFggufgguf1,705MiniMaxAI/MiniMax-M2
granite-4.0-h-small-GGUFggufgguf1,695ibm-granite/granite-4.0-h-small
GLM-4-32B-0414-GGUFggufgguf1,668THUDM/GLM-4-32B-0414
gemma-3-270m-it-qat-MLX-4bitggufgguf1,668google/gemma-3-270m-it-qat-q4_0-unquantized
Llama-4-Scout-17B-16E-Instruct-GGUFggufgguf1,667meta-llama/Llama-4-Scout-17B-16E-Instruct
Qwen3-30B-A3B-Thinking-2507-GGUFggufgguf1,652Qwen/Qwen3-30B-A3B-Thinking-2507
LFM2.5-1.2B-Thinking-MLX-8bitmlxmlx1,644LiquidAI/LFM2.5-1.2B-Thinking
gemma-3-4B-it-qat-GGUFggufgguf1,636google/gemma-3-4b-it
Qwen2.5-14B-Instruct-MLX-8bitmlxmlx1,606Qwen/Qwen2.5-14B-Instruct
Qwen2.5-72B-Instruct-GGUFggufgguf1,602Qwen/Qwen2.5-72B-Instruct
Qwen3-VL-32B-Instruct-MLX-6bitmlxmlx1,588Qwen/Qwen3-VL-32B-Instruct
Qwen3-235B-A22B-GGUFggufgguf1,582Qwen/Qwen3-235B-A22B
OpenCodeReasoning-Nemotron-32B-GGUFggufgguf1,573nvidia/OpenCodeReasoning-Nemotron-32B
Qwen3-Next-80B-A3B-Thinking-GGUFggufgguf1,565Qwen/Qwen3-Next-80B-A3B-Thinking
GLM-4.5-Air-GGUFggufgguf1,502zai-org/GLM-4.5-Air
Qwen2.5-Coder-3B-Instruct-MLX-8bitmlxmlx1,492Qwen/Qwen2.5-Coder-3B-Instruct
Qwen2.5-Coder-0.5B-Instruct-MLX-4bitmlxmlx1,481Qwen/Qwen2.5-Coder-0.5B-Instruct
GLM-Z1-32B-0414-GGUFggufgguf1,475THUDM/GLM-Z1-32B-0414
Meta-Llama-3.1-70B-Instruct-GGUFggufgguf1,468meta-llama/Meta-Llama-3.1-70B-Instruct
Qwen2-VL-2B-Instruct-GGUFggufgguf1,443Qwen/Qwen2-VL-2B
Qwen2.5-Math-7B-Instruct-GGUFggufgguf1,422Qwen/Qwen2.5-Math-7B-Instruct
deepseek-coder-1.3B-kexer-GGUFggufgguf1,415JetBrains/deepseek-coder-1.3B-kexer
Phi-3.1-mini-128k-instruct-GGUFggufgguf1,378microsoft/Phi-3-mini-128k-instruct
gemma-3-12B-it-qat-GGUFggufgguf1,377google/gemma-3-12b-it
granite-4.0-micro-GGUFggufgguf1,366ibm-granite/granite-4.0-micro
Yi-Coder-9B-Chat-GGUFggufgguf1,36501-ai/Yi-Coder-9B-Chat
GLM-Z1-Rumination-32B-0414-GGUFggufgguf1,345THUDM/GLM-Z1-Rumination-32B-0414
GLM-4-9B-0414-GGUFggufgguf1,320THUDM/GLM-4-9B-0414
Olmo-3-1125-32B-GGUFggufgguf1,318allenai/Olmo-3-1125-32B
Olmo-3.1-32B-Think-GGUFggufgguf1,316allenai/Olmo-3.1-32B-Think
Mistral-Small-24B-Instruct-2501-GGUFggufgguf1,299mistralai/Mistral-Small-24B-Instruct-2501
QwQ-32B-Preview-GGUFggufgguf1,287Qwen/QwQ-32B-Preview
OpenCodeReasoning-Nemotron-32B-IOI-GGUFggufgguf1,287nvidia/OpenCodeReasoning-Nemotron-32B-IOI
INTELLECT-2-GGUFggufgguf1,287PrimeIntellect/INTELLECT-2
Olmo-3.1-32B-Instruct-GGUFggufgguf1,276allenai/Olmo-3.1-32B-Instruct
Skywork-R1V3-38B-GGUFggufgguf1,270Skywork/Skywork-R1V3-38B
Qwen2.5-7B-Instruct-MLX-8bitmlxmlx1,265Qwen/Qwen2.5-7B-Instruct
openhands-lm-32b-v0.1-GGUFggufgguf1,258all-hands/openhands-lm-32b-v0.1
OlympicCoder-32B-GGUFggufgguf1,251open-r1/OlympicCoder-32B
Skywork-SWE-32B-GGUFggufgguf1,251Skywork/Skywork-SWE-32B
DeepSWE-Preview-GGUFggufgguf1,245agentica-org/DeepSWE-Preview
AM-Thinking-v1-GGUFggufgguf1,242a-m-team/AM-Thinking-v1
OpenThinker-32B-GGUFggufgguf1,241open-thoughts/OpenThinker-32B
zeta-GGUFggufgguf1,240zed-industries/zeta
OREAL-32B-GGUFggufgguf1,235internlm/OREAL-32B
Qwen3.5-397B-A17B-MLX-4bitmlxmlx1,200Qwen/Qwen3.5-397B-A17B
gpt-oss-safeguard-20b-GGUFggufgguf1,187openai/gpt-oss-safeguard-20b
Yi-1.5-34B-Chat-GGUFggufgguf1,16601-ai/Yi-1.5-34B-Chat
Qwen3.5-397B-A17B-MLX-6bitmlxmlx1,147Qwen/Qwen3.5-397B-A17B
gemma-3-270m-it-MLX-bf16mlxmlx1,144google/gemma-3-270m-it
Qwen2.5-32B-Instruct-MLX-4bitmlxmlx1,119Qwen/Qwen2.5-32B-Instruct
sarvam-m-GGUFggufgguf1,095sarvamai/sarvam-m
gpt-oss-safeguard-120b-GGUFggufgguf1,090openai/gpt-oss-safeguard-120b
GLM-Z1-9B-0414-GGUFggufgguf1,081THUDM/GLM-Z1-9B-0414
Llama-4-Scout-17B-16E-MLX-text-4bitmlxmlx1,072meta-llama/Llama-4-Scout-17B-16E-Instruct
Mistral-Small-4-119B-2603-GGUFggufgguf1,072mistralai/Mistral-Small-4-119B-2603
WizardLM-2-7B-GGUFggufgguf1,046fearlessdots/WizardLM-2-7B-abliterated
UI-TARS-72B-DPO-GGUFggufgguf1,003bytedance-research/UI-TARS-72B-DPO
DeepSeek-V3-0324-GGUFggufgguf1,000deepseek-ai/DeepSeek-V3-0324
Qwen3-VL-235B-A22B-Thinking-GGUFggufgguf988Qwen/Qwen3-VL-235B-A22B-Thinking
reka-flash-3.1-GGUFggufgguf987RekaAI/reka-flash-3.1
Qwen2.5-Math-72B-Instruct-GGUFggufgguf985Qwen/Qwen2.5-Math-72B-Instruct
Qwen2.5-3B-Instruct-MLX-4bitmlxmlx968Qwen/Qwen2.5-3B-Instruct
Yi-1.5-9B-Chat-GGUFggufgguf96301-ai/Yi-1.5-9B-Chat
Qwen3-VL-4B-Thinking-GGUFggufgguf953Qwen/Qwen3-VL-4B-Thinking
aya-expanse-8b-GGUFggufgguf947CohereForAI/aya-expanse-8b
Magistral-Small-2507-GGUFggufgguf923mistralai/Magistral-Small-2507
UI-TARS-7B-DPO-GGUFggufgguf918bytedance-research/UI-TARS-7B-DPO
GLM-4.5-Air-MLX-4bitmlxmlx918zai-org/GLM-4.5-Air
Meta-Llama-3-70B-Instruct-GGUFggufgguf899meta-llama/Meta-Llama-3-70B-Instruct
gemma-1.1-2b-it-GGUFggufgguf893google/gemma-1.1-2b-it
nomic-embed-code-GGUFggufgguf893nomic-ai/nomic-embed-code
Qwen2.5-Coder-0.5B-Instruct-MLX-8bitmlxmlx889Qwen/Qwen2.5-Coder-0.5B-Instruct
LFM2.5-VL-1.6B-GGUFggufgguf889LiquidAI/LFM2.5-VL-1.6B
OpenCodeReasoning-Nemotron-14B-GGUFggufgguf868nvidia/OpenCodeReasoning-Nemotron-14B
codegemma-1.1-7b-it-GGUFggufgguf865google/codegemma-1.1-7b-it
reka-flash-3-GGUFggufgguf856RekaAI/reka-flash-3
r1-1776-distill-llama-70b-GGUFggufgguf844perplexity-ai/r1-1776-distill-llama-70b
InternVL3_5-8B-GGUFggufgguf820OpenGVLab/InternVL3_5-8B
SmolLM3-3B-MLX-8bitmlxmlx785HuggingFaceTB/SmolLM3-3B
CodeLlama-7B-KStack-clean-GGUFggufgguf764JetBrains/CodeLlama-7B-KStack-clean
SmolLM2-135M-Instruct-GGUFggufgguf761HuggingFaceTB/SmolLM2-135M-Instruct
Devstral-2-123B-Instruct-2512-GGUFggufgguf760mistralai/Devstral-2-123B-Instruct-2512
gemma-3-270m-it-qat-GGUFggufgguf759google/gemma-3-270m-it-qat-q4_0-unquantized
gemma-3-270m-it-MLX-4bitmlxmlx759google/gemma-3-270m-it
Qwen3-235B-A22B-Thinking-2507-MLX-8bitmlxmlx750Qwen/Qwen3-235B-A22B-Thinking-2507
Qwen2.5-32B-Instruct-MLX-8bitmlxmlx749Qwen/Qwen2.5-32B-Instruct
GLM-4.5-Air-MLX-6bitmlxmlx739zai-org/GLM-4.5-Air
Apriel-Nemotron-15b-Thinker-GGUFggufgguf735ServiceNow-AI/Apriel-Nemotron-15b-Thinker
granite-4.0-h-micro-GGUFggufgguf733ibm-granite/granite-4.0-h-micro
codegemma-7b-it-GGUFggufgguf721google/codegemma-7b
Qwen3-VL-32B-Instruct-MLX-4bitmlxmlx719Qwen/Qwen3-VL-32B-Instruct
LFM2.5-VL-1.6B-MLX-6bitmlxmlx706LiquidAI/LFM2.5-VL-1.6B
granite-3.0-3b-a800m-instruct-GGUFggufgguf701ibm-granite/granite-3.0-3b-a800m-instruct
medgemma-4b-it-GGUFggufgguf700google/medgemma-4b-it
Olmo-3.1-32B-Instruct-MLX-4bitmlxmlx698allenai/Olmo-3.1-32B-Instruct
Phi-4-reasoning-GGUFggufgguf697microsoft/Phi-4-reasoning
EXAONE-4.0-32B-MLX-4bitmlxmlx697LGAI-EXAONE/EXAONE-4.0-32B
Ling-lite-0415-GGUFggufgguf677inclusionAI/Ling-lite
MiniCPM-o-2_6-GGUFggufgguf674openbmb/MiniCPM-o-2_6
Qwen3-VL-32B-Instruct-MLX-8bitmlxmlx669Qwen/Qwen3-VL-32B-Instruct
LFM2.5-VL-1.6B-MLX-8bitmlxmlx667LiquidAI/LFM2.5-VL-1.6B
granite-vision-3.2-2b-GGUFggufgguf665ibm-granite/granite-vision-3.2-2b
medgemma-4b-it-MLX-4bitmlxmlx660google/medgemma-4b-it
Qwen3.5-397B-A17B-GGUFggufgguf654Qwen/Qwen3.5-397B-A17B
granite-3.3-8b-instruct-GGUFggufgguf643ibm-granite/granite-3.3-8b-instruct
Qwen2.5-3B-Instruct-MLX-8bitmlxmlx638Qwen/Qwen2.5-3B-Instruct
InternVL3_5-14B-GGUFggufgguf636OpenGVLab/InternVL3_5-14B
CodeLlama-7B-KStack-GGUFggufgguf625JetBrains/CodeLlama-7B-KStack
UI-TARS-2B-SFT-GGUFggufgguf621bytedance-research/UI-TARS-2B-SFT
granite-4.0-h-tiny-MLX-8bitmlxmlx619ibm-granite/granite-4.0-h-tiny
Qwen2.5-0.5B-Instruct-MLX-8bitmlxmlx618Qwen/Qwen2.5-0.5B-Instruct
Olmo-3-7B-Instruct-GGUFggufgguf592allenai/Olmo-3-7B-Instruct
starcoder2-15b-instruct-v0.1-GGUFggufgguf591bigcode/starcoder2-15b
Qwen2-500M-Instruct-GGUFggufgguf590Qwen/Qwen2-0.5B-Instruct
Qwen3-30B-A3B-Thinking-2507-MLX-8bitmlxmlx589Qwen/Qwen3-30B-A3B-Thinking-2507
medgemma-27b-text-it-GGUFggufgguf588google/medgemma-27b-text-it
Meta-Llama-3-120B-Instruct-GGUFggufgguf580mlabonne/Meta-Llama-3-120B-Instruct
Dhanishtha-2.0-preview-GGUFggufgguf574HelpingAI/Dhanishtha-2.0-preview
functiongemma-270m-it-MLX-8bitmlxmlx572google/functiongemma-270m-it
Qwen2.5-1.5B-Instruct-MLX-4bitmlxmlx570Qwen/Qwen2.5-1.5B-Instruct
AlchemistCoder-DS-6.7B-GGUFggufgguf569internlm/AlchemistCoder-DS-6.7B
Qwen3-VL-32B-Thinking-MLX-4bitmlxmlx568Qwen/Qwen3-VL-32B-Thinking
Starling-LM-7B-beta-GGUFggufgguf563—
stable-code-instruct-3b-GGUFggufgguf562—
c4ai-command-r-08-2024-GGUFggufgguf560CohereForAI/c4ai-command-r-08-2024
INTELLECT-1-Instruct-GGUFggufgguf556PrimeIntellect/INTELLECT-1-Instruct
gemma-3n-E2B-it-MLX-4bitmlxmlx555google/gemma-3n-E2B-it
c4ai-command-r-plus-08-2024-GGUFggufgguf552CohereForAI/c4ai-command-r-plus-08-2024
Qwen3-30B-A3B-Thinking-2507-MLX-4bitmlxmlx548Qwen/Qwen3-30B-A3B-Thinking-2507
EuroLLM-9B-Instruct-GGUFggufgguf545utter-project/EuroLLM-9B-Instruct
SmolLM3-3B-GGUFggufgguf537HuggingFaceTB/SmolLM3-3B
Qwen3-VL-8B-Thinking-MLX-4bitmlxmlx531Qwen/Qwen3-VL-8B-Thinking
Hermes-4-405B-MLX-4bitmlxmlx525NousResearch/Hermes-4-405B
gemma-3-270m-it-GGUFggufgguf522google/gemma-3-270m-it
wavecoder-ultra-6.7b-GGUFggufgguf501microsoft/wavecoder-ultra-6.7b
Qwen3-VL-235B-A22B-Instruct-GGUFggufgguf492Qwen/Qwen3-VL-235B-A22B-Instruct
Qwen3-VL-2B-Instruct-MLX-bf16mlxmlx483Qwen/Qwen3-VL-2B-Instruct
Qwen3-30B-A3B-Thinking-2507-MLX-6bitmlxmlx479Qwen/Qwen3-30B-A3B-Thinking-2507
Yi-1.5-6B-Chat-GGUFggufgguf47601-ai/Yi-1.5-6B-Chat
Qwen2.5-Math-1.5B-Instruct-GGUFggufgguf450Qwen/Qwen2.5-Math-1.5B-Instruct
InternVL3_5-30B-A3B-GGUFggufgguf447OpenGVLab/InternVL3_5-30B-A3B
Qwen3-VL-2B-Thinking-GGUFggufgguf447Qwen/Qwen3-VL-2B-Thinking
Qwen2.5-Coder-0.5B-GGUFggufgguf444Qwen/Qwen2.5-Coder-0.5B
LFM2-VL-450M-GGUFggufgguf440LiquidAI/LFM2-VL-450M
functiongemma-270m-it-GGUFggufgguf440google/functiongemma-270m-it
Phi-4-reasoning-MLX-4bitmlxmlx433microsoft/Phi-4-reasoning
olmOCR-7B-0225-preview-GGUFggufgguf431allenai/olmOCR-7B-0225-preview
SmolLM2-360M-Instruct-GGUFggufgguf429HuggingFaceTB/SmolLM2-360M-Instruct
granite-3.0-8b-instruct-GGUFggufgguf426ibm-granite/granite-3.0-8b-instruct
Mistral-Large-Instruct-2411-GGUFggufgguf425mistralai/Mistral-Large-Instruct-2411
Llama-3.1-Tulu-3-70B-GGUFggufgguf424allenai/Llama-3.1-Tulu-3-70B
granite-3.3-2b-instruct-GGUFggufgguf424ibm-granite/granite-3.3-2b-instruct
OpenCodeReasoning-Nemotron-7B-GGUFggufgguf418nvidia/OpenCodeReasoning-Nemotron-7B
codegemma-2b-GGUFggufgguf415google/codegemma-2b
internlm3-8b-instruct-GGUFggufgguf408internlm/internlm3-8b-instruct
Qwen3-VL-2B-Instruct-MLX-8bitmlxmlx406Qwen/Qwen3-VL-2B-Instruct
gemma-3n-E2B-it-MLX-6bitmlxmlx405google/gemma-3n-E2B-it
Qwen3-VL-2B-Thinking-MLX-8bitmlxmlx403Qwen/Qwen3-VL-2B-Thinking
Qwen2.5-1.5B-Instruct-MLX-8bitmlxmlx402Qwen/Qwen2.5-1.5B-Instruct
Olmo-3-7B-Think-GGUFggufgguf400allenai/Olmo-3-7B-Think
openhands-lm-7b-v0.1-GGUFggufgguf397all-hands/openhands-lm-7b-v0.1
c4ai-command-r-v01-GGUFggufgguf395—
Qwen3-235B-A22B-Thinking-2507-MLX-4bitmlxmlx394Qwen/Qwen3-235B-A22B-Thinking-2507
DeepCoder-14B-Preview-GGUFggufgguf391agentica-org/DeepCoder-14B-Preview
mathstral-7B-v0.1-GGUFggufgguf389mistralai/mathstral-7B-v0.1
OpenMath-Nemotron-32B-GGUFggufgguf387nvidia/OpenMath-Nemotron-32B
Qwen2-VL-72B-Instruct-GGUFggufgguf384Qwen/Qwen2-VL-72B-Instruct
OpenReasoning-Nemotron-14B-GGUFggufgguf384nvidia/OpenReasoning-Nemotron-14B
Hermes-4-405B-MLX-8bitmlxmlx377NousResearch/Hermes-4-405B
cogito-v1-preview-qwen-32B-GGUFggufgguf374deepcogito/cogito-v1-preview-qwen-32B
DeepSeek-R1-0528-GGUFggufgguf374deepseek-ai/DeepSeek-R1-0528
Olmo-3-1025-7B-GGUFggufgguf370allenai/Olmo-3-1025-7B
r1-1776-GGUFggufgguf369perplexity-ai/r1-1776
ByteCraft-GGUFggufgguf364SamsungSAILMontreal/ByteCraft
granite-3.1-3b-a800m-instruct-GGUFggufgguf360ibm-granite/granite-3.1-3b-a800m-instruct
AlchemistCoder-L-7B-GGUFggufgguf359internlm/AlchemistCoder-L-7B
DeepSeek-V2.5-GGUFggufgguf352deepseek-ai/DeepSeek-V2.5
OlympicCoder-7B-GGUFggufgguf348open-r1/OlympicCoder-7B
LFM2.5-350M-GGUFggufgguf346LiquidAI/LFM2.5-350M
internlm2-math-plus-20b-GGUFggufgguf345internlm/internlm2-math-plus-20b
Llama-3-Groq-8B-Tool-Use-GGUFggufgguf339Groq/Llama-3-Groq-8B-Tool-Use
Qwen1.5-32B-Chat-GGUFggufgguf338Qwen/Qwen1.5-32B
aya-23-35B-GGUFggufgguf334CohereForAI/aya-23-35B
Hermes-4-405B-MLX-6bitmlxmlx331NousResearch/Hermes-4-405B
Qwen3-VL-32B-Instruct-MLX-5bitmlxmlx330Qwen/Qwen3-VL-32B-Instruct
Qwen2-Math-7B-Instruct-GGUFggufgguf328Qwen/Qwen2-Math-7B-Instruct
OpenThinker3-7B-GGUFggufgguf325open-thoughts/OpenThinker3-7B
Mistral-Large-Instruct-2407-GGUFggufgguf322mistralai/Mistral-Large-Instruct-2407
Qwen3-Next-80B-A3B-Thinking-MLX-4bitmlxmlx322Qwen/Qwen3-Next-80B-A3B-Thinking
gemma-2b-aps-it-GGUFggufgguf318google/gemma-2b-aps-it
KAT-Dev-MLX-4bitmlxmlx316Kwaipilot/KAT-Dev
OREAL-7B-GGUFggufgguf309internlm/OREAL-7B
ERNIE-4.5-0.3B-GGUFggufgguf308baidu/ERNIE-4.5-0.3B-PT
granite-embedding-278m-multilingual-GGUFggufgguf306ibm-granite/granite-embedding-278m-multilingual
Jedi-7B-1080p-GGUFggufgguf306xlangai/Jedi-7B-1080p
OpenThinker2-32B-GGUFggufgguf305open-thoughts/OpenThinker2-32B
Qwen3-VL-30B-A3B-Thinking-MLX-8bitmlxmlx305Qwen/Qwen3-VL-30B-A3B-Thinking
functiongemma-270m-it-MLX-bf16mlxmlx301google/functiongemma-270m-it
Qwen3-235B-A22B-Thinking-2507-GGUFggufgguf299Qwen/Qwen3-235B-A22B-Thinking-2507
Yi-Coder-1.5B-Chat-GGUFggufgguf29101-ai/Yi-Coder-1.5B-Chat
dots.llm1.inst-GGUFggufgguf288rednote-hilab/dots.llm1.inst
LFM2.5-1.2B-Thinking-MLX-bf16mlxmlx287LiquidAI/LFM2.5-1.2B-Thinking
Qwen3-235B-A22B-Thinking-2507-MLX-6bitmlxmlx276Qwen/Qwen3-235B-A22B-Thinking-2507
Hyperion-3.0-Mistral-7B-DPO-GGUFggufgguf273—
Llama-3.1-8B-UltraLong-1M-Instruct-GGUFggufgguf270nvidia/Llama-3.1-8B-UltraLong-1M-Instruct
Meta-Llama-3-8B-Instruct-BPE-fix-GGUFggufgguf266meta-llama/Meta-Llama-3-8B-Instruct
gemma-3n-E2B-it-MLX-8bitmlxmlx263google/gemma-3n-E2B-it
Qwen3-VL-32B-Thinking-MLX-6bitmlxmlx258Qwen/Qwen3-VL-32B-Thinking
Qwen3-VL-30B-A3B-Thinking-MLX-4bitmlxmlx256Qwen/Qwen3-VL-30B-A3B-Thinking
codegemma-7b-GGUFggufgguf255google/codegemma-7b-it
EXAONE-4.0.1-32B-GGUFggufgguf245LGAI-EXAONE/EXAONE-4.0.1-32B
aya-expanse-32b-GGUFggufgguf239CohereForAI/aya-expanse-32b
rnj-1-instruct-MLX-8bitmlxmlx238EssentialAI/rnj-1-instruct
granite-3.1-1b-a400m-instruct-GGUFggufgguf232ibm-granite/granite-3.1-1b-a400m-instruct
Llama3-ChatQA-1.5-70B-GGUFggufgguf231nvidia/Llama3-ChatQA-1.5-70B
InternVL3_5-4B-GGUFggufgguf227OpenGVLab/InternVL3_5-4B
Qwen3-VL-8B-Thinking-MLX-8bitmlxmlx227Qwen/Qwen3-VL-8B-Thinking
gemma-3n-E2B-it-MLX-bf16mlxmlx225google/gemma-3n-E2B-it
Devstral-Small-2505-MLX-6bitmlxmlx223mistralai/Devstral-Small-2505
internlm2-math-plus-7b-GGUFggufgguf217internlm/internlm2-math-plus-7b
OpenCoder-8B-Instruct-GGUFggufgguf215infly/OpenCoder-8B-Instruct
GLM-4.7-GGUFggufgguf215zai-org/GLM-4.7
Qwen2-Math-1.5B-Instruct-GGUFggufgguf209Qwen/Qwen2-Math-1.5B-Instruct
granite-3.2-2b-instruct-GGUFggufgguf209ibm-granite/granite-3.2-2b-instruct
Qwen3-Next-80B-A3B-Thinking-MLX-8bitmlxmlx206Qwen/Qwen3-Next-80B-A3B-Thinking
Llama3-ChatQA-1.5-8B-GGUFggufgguf205nvidia/Llama3-ChatQA-1.5-8B
Falcon3-10B-Instruct-GGUFggufgguf204tiiuae/Falcon3-10B-Instruct
SmolLM3-3B-MLX-4bitmlxmlx203HuggingFaceTB/SmolLM3-3B
LFM2-VL-1.6B-GGUFggufgguf203LiquidAI/LFM2-VL-1.6B
DeepSeek-V2.5-1210-GGUFggufgguf196deepseek-ai/DeepSeek-V2.5-1210
granite-4.0-h-small-MLX-6bitmlxmlx195ibm-granite/granite-4.0-h-small
Qwen2-Math-72B-Instruct-GGUFggufgguf188Qwen/Qwen2-Math-72B-Instruct
OpenReasoning-Nemotron-7B-GGUFggufgguf188nvidia/OpenReasoning-Nemotron-7B
granite-3.0-2b-instruct-GGUFggufgguf185ibm-granite/granite-3.0-2b-instruct
LFM2-350M-MLX-8bitmlxmlx182LiquidAI/LFM2-350M
granite-4.0-h-small-MLX-4bitmlxmlx181ibm-granite/granite-4.0-h-small
granite-3.1-2b-instruct-GGUFggufgguf174ibm-granite/granite-3.1-2b-instruct
Qwen3-VL-30B-A3B-Thinking-MLX-6bitmlxmlx169Qwen/Qwen3-VL-30B-A3B-Thinking
LFM2.5-VL-1.6B-MLX-4bitmlxmlx168LiquidAI/LFM2.5-VL-1.6B
granite-4.0-h-tiny-MLX-6bitmlxmlx166ibm-granite/granite-4.0-h-tiny
FineMath-Llama-3B-GGUFggufgguf165HuggingFaceTB/FineMath-Llama-3B
OpenReasoning-Nemotron-32B-GGUFggufgguf163nvidia/OpenReasoning-Nemotron-32B
internlm2-math-plus-mixtral8x22b-GGUFggufgguf161internlm/internlm2-math-plus-mixtral8x22b
aya-23-8B-GGUFggufgguf160CohereForAI/aya-23-8B
cogito-v1-preview-qwen-14B-GGUFggufgguf159deepcogito/cogito-v1-preview-qwen-14B
QVQ-72B-Preview-GGUFggufgguf157Qwen/QVQ-72B-Preview
openchat-3.6-8b-20240522-GGUFggufgguf156openchat/openchat-3.6-8b-20240522
Jedi-3B-1080p-GGUFggufgguf155xlangai/Jedi-3B-1080p
granite-4.0-h-tiny-MLX-4bitmlxmlx154ibm-granite/granite-4.0-h-tiny
DiscoPOP-zephyr-7b-gemma-GGUFggufgguf150SakanaAI/DiscoPOP-zephyr-7b-gemma
granite-embedding-107m-multilingual-GGUFggufgguf150ibm-granite/granite-embedding-107m-multilingual
c4ai-command-a-03-2025-GGUFggufgguf150CohereForAI/c4ai-command-a-03-2025
Llama-3_1-Nemotron-Ultra-253B-v1-GGUFggufgguf149nvidia/Llama-3_1-Nemotron-Ultra-253B-v1
InternVL3_5-2B-GGUFggufgguf147OpenGVLab/InternVL3_5-2B
Qwen3-Next-80B-A3B-Thinking-MLX-6bitmlxmlx147Qwen/Qwen3-Next-80B-A3B-Thinking
Qwen3-VL-32B-Thinking-MLX-5bitmlxmlx145Qwen/Qwen3-VL-32B-Thinking
Llama-3-Groq-70B-Tool-Use-GGUFggufgguf138Groq/Llama-3-Groq-8B-Tool-Use
DeepCoder-1.5B-Preview-GGUFggufgguf134agentica-org/DeepCoder-1.5B-Preview
EXAONE-4.0-32B-MLX-8bitmlxmlx134LGAI-EXAONE/EXAONE-4.0-32B
Olmo-3.1-32B-Think-MLX-4bitmlxmlx133allenai/Olmo-3.1-32B-Think
GLM-4.5-GGUFggufgguf132zai-org/GLM-4.5
Qwen3-Next-80B-A3B-Thinking-MLX-5bitmlxmlx132Qwen/Qwen3-Next-80B-A3B-Thinking
granite-embedding-30m-english-GGUFggufgguf131ibm-granite/granite-embedding-30m-english
LFM2-350M-MLX-bf16mlxmlx131LiquidAI/LFM2-350M
Llama-3.1-Nemotron-Nano-4B-v1.1-GGUFggufgguf130nvidia/Llama-3.1-Nemotron-Nano-4B-v1.1
EXAONE-4.0-1.2B-GGUFggufgguf130LGAI-EXAONE/EXAONE-4.0-1.2B
AceReason-Nemotron-14B-GGUFggufgguf126nvidia/AceReason-Nemotron-14B
granite-4.0-h-small-MLX-5bitmlxmlx126ibm-granite/granite-4.0-h-small
Mistral-Small-Instruct-2409-GGUFggufgguf122mistralai/Mistral-Small-Instruct-2409
OpenReasoning-Nemotron-1.5B-GGUFggufgguf120nvidia/OpenReasoning-Nemotron-1.5B
EXAONE-Deep-7.8B-GGUFggufgguf117LGAI-EXAONE/EXAONE-Deep-7.8B
Qwen3-VL-8B-Thinking-MLX-6bitmlxmlx117Qwen/Qwen3-VL-8B-Thinking
granite-3.0-1b-a400m-instruct-GGUFggufgguf116ibm-granite/granite-3.0-1b-a400m-instruct
Qwen3-VL-8B-Thinking-MLX-5bitmlxmlx116Qwen/Qwen3-VL-8B-Thinking
AMD-OLMo-1B-SFT-GGUFggufgguf115amd/AMD-OLMo-1B-SFT
Hunyuan-A13B-Instruct-GGUFggufgguf115tencent/Hunyuan-A13B-Instruct
Athene-70B-GGUFggufgguf113Nexusflow/Athene-70B
Athene-V2-Agent-GGUFggufgguf113Nexusflow/Athene-V2-Agent
gemma-7b-aps-it-GGUFggufgguf112google/gemma-7b-aps-it
granite-embedding-125m-english-GGUFggufgguf109ibm-granite/granite-embedding-125m-english
txgemma-9b-chat-GGUFggufgguf106google/txgemma-9b-chat
ZR1-1.5B-GGUFggufgguf105Zyphra/ZR1-1.5B
InternVL3_5-1B-GGUFggufgguf105OpenGVLab/InternVL3_5-1B
granite-4.0-h-tiny-MLX-5bitmlxmlx105ibm-granite/granite-4.0-h-tiny
Qwen3-VL-30B-A3B-Thinking-MLX-5bitmlxmlx104Qwen/Qwen3-VL-30B-A3B-Thinking
Hermes-4-405B-GGUFggufgguf101NousResearch/Hermes-4-405B
Meta-Llama-3-70B-Instruct-BPE-fix-GGUFggufgguf100meta-llama/Meta-Llama-3-70B-Instruct
cogito-v1-preview-llama-8B-GGUFggufgguf97deepcogito/cogito-v1-preview-llama-8B
Skywork-OR1-7B-GGUFggufgguf95Skywork/Skywork-OR1-7B
SmolLM3-3B-MLX-6bitmlxmlx95HuggingFaceTB/SmolLM3-3B
KAT-Dev-MLX-6bitmlxmlx95Kwaipilot/KAT-Dev
Qwen3-VL-4B-Thinking-MLX-4bitmlxmlx95Qwen/Qwen3-VL-4B-Thinking
LFM2-700M-MLX-8bitmlxmlx89LiquidAI/LFM2-700M
Llama-3_1-Nemotron-51B-Instruct-GGUFggufgguf88nvidia/Llama-3_1-Nemotron-51B-Instruct
openhands-lm-1.5b-v0.1-GGUFggufgguf86all-hands/openhands-lm-1.5b-v0.1
KAT-Dev-MLX-5bitmlxmlx81Kwaipilot/KAT-Dev
Olmo-3.1-32B-Instruct-MLX-8bitmlxmlx81allenai/Olmo-3.1-32B-Instruct
OpenThinker2-7B-GGUFggufgguf80open-thoughts/OpenThinker2-7B
Olmo-3-7B-Think-MLX-8bitmlxmlx80allenai/Olmo-3-7B-Think
xLAM-7b-r-GGUFggufgguf79Salesforce/xLAM-7b-r
EXAONE-4.0-1.2B-MLX-4bitmlxmlx76LGAI-EXAONE/EXAONE-4.0-1.2B
ERNIE-4.5-0.3B-MLX-bf16mlxmlx74baidu/ERNIE-4.5-0.3B-PT
Qwen3-4B-Thinking-2507-MLX-5bitmlxmlx72Qwen/Qwen3-4B-Thinking-2507
Qwen3-VL-4B-Thinking-MLX-8bitmlxmlx71Qwen/Qwen3-VL-4B-Thinking
AceInstruct-72B-GGUFggufgguf70nvidia/AceInstruct-72B
cogito-v1-preview-llama-3B-GGUFggufgguf70deepcogito/cogito-v1-preview-llama-3B
Olmo-3-7B-Instruct-MLX-4bitmlxmlx68allenai/Olmo-3-7B-Instruct
internlm2_5-20b-chat-GGUFggufgguf66internlm/internlm2_5-20b-chat
Olmo-3-1125-32B-MLX-8bitmlxmlx65allenai/Olmo-3-1125-32B
Olmo-3-7B-Think-MLX-4bitmlxmlx64allenai/Olmo-3-7B-Think
Llama-3.1-Tulu-3-405B-GGUFggufgguf63allenai/Llama-3.1-Tulu-3-405B
OpenMath-Nemotron-14B-GGUFggufgguf63nvidia/OpenMath-Nemotron-14B
Olmo-3-7B-Instruct-MLX-8bitmlxmlx62allenai/Olmo-3-7B-Instruct
Skywork-OR1-Math-7B-GGUFggufgguf58Skywork/Skywork-OR1-Math-7B
AFM-4.5B-GGUFggufgguf54arcee-ai/AFM-4.5B
Qwen3-VL-4B-Thinking-MLX-5bitmlxmlx54Qwen/Qwen3-VL-4B-Thinking
AceReason-Nemotron-1.1-7B-GGUFggufgguf53nvidia/AceReason-Nemotron-1.1-7B
Olmo-3.1-32B-Think-MLX-8bitmlxmlx53allenai/Olmo-3.1-32B-Think
Falcon3-7B-Instruct-GGUFggufgguf51tiiuae/Falcon3-7B-Instruct
Falcon3-3B-Instruct-GGUFggufgguf51tiiuae/Falcon3-3B-Instruct
Olmo-3.1-32B-Think-MLX-6bitmlxmlx51allenai/Olmo-3.1-32B-Think
datagemma-rag-27b-it-GGUFggufgguf50google/datagemma-rag-27b-it
Olmo-3-1025-7B-MLX-8bitmlxmlx49allenai/Olmo-3-1025-7B
functiongemma-270m-it-MLX-6bitmlxmlx48google/functiongemma-270m-it
Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.