family llama · 5 variants · unknown
| benchmark | category | best score |
|---|---|---|
| MATH | math | 95.4 |
| variant | kind | quant | bits | vRAM | dl | org | year |
|---|---|---|---|---|---|---|---|
| Llama-3.1-Nemotron-Nano-8B-v1 | original | bf16 | 16.0 | 52,529 | nvidia | 2025 | |
| Llama-3.1-Nemotron-Nano-8B-v1-GGUF | gguf | gguf | 16.0 | 3,384 | unsloth | 2025 | |
| nvidia_Llama-3.1-Nemotron-Nano-8B-v1-GGUF | gguf | gguf | 2.0 | 730 | bartowski | 2025 | |
| Llama-3.1-Nemotron-Nano-8B-v1-GGUF | gguf | gguf | 16.0 | 259 | Mungert | 2025 | |
| DLER-Llama-Nemotron-8B-Merge-Research | merge | merge | 65 | nvidia | 2025 |