family llama · 5 variants · unknown
| benchmark | category | best score |
|---|---|---|
| MATH | math | 89.29 |
| variant | kind | quant | bits | vRAM | dl | org | year |
|---|---|---|---|---|---|---|---|
| Llama-3_1-Nemotron-Ultra-253B-v1 | original | bf16 | 16.0 | 2,928 | nvidia | 2025 | |
| Llama-3_1-Nemotron-Ultra-253B-v1-GGUF | gguf | gguf | 16.0 | 1,541 | unsloth | 2025 | |
| Llama-3_1-Nemotron-Ultra-253B-v1-FP8 | fp8 | fp8 | 8.0 | 734 | nvidia | 2025 | |
| nvidia_Llama-3_1-Nemotron-Ultra-253B-v1-GGUF | gguf | gguf | 1.0 | 458 | bartowski | 2025 | |
| Llama-3_1-Nemotron-Ultra-253B-v1-GGUF | gguf | gguf | 3.0 | 149 | lmstudio-community | 2025 |