Nemotron 3 Nano 30B-A3B
17 records across 3 hardware.
| hardware | model | quant | backend | tok/s | pp tok/s | W | ttft s | ctx/tg | date | class | flags | source |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| RTX PRO 6000 | Nemotron 3 Nano 30B-A3B 30B | NVFP4 | llama.cpp (CUDA) | 3159.1 | – | – | – | – | 2026-08 | community | – | source |
| RTX PRO 6000 | Nemotron 3 Nano 30B-A3B 30B | NVFP4 | llama.cpp (CUDA) | 2132.4 | – | – | – | – | 2026-08 | community | – | source |
| RTX PRO 6000 | Nemotron 3 Nano 30B-A3B 30B | NVFP4 | llama.cpp (CUDA) | 1959.8 | – | – | – | – | 2026-08 | community | – | source |
| RTX PRO 6000 | Nemotron 3 Nano 30B-A3B 30B | NVFP4 | llama.cpp (CUDA) | 1542.0 | – | – | – | – | 2026-08 | community | – | source |
| RTX PRO 6000 | Nemotron 3 Nano 30B-A3B 30B | NVFP4 | llama.cpp (CUDA) | 1234.1 | – | – | – | – | 2026-08 | community | – | source |
| RTX PRO 6000 | Nemotron 3 Nano 30B-A3B 30B | NVFP4 | llama.cpp (CUDA) | 1035.5 | – | – | – | – | 2026-08 | community | – | source |
| GB10 | Nemotron 3 Nano 30B-A3B 30B | NVFP4 | llama.cpp (CUDA) | 660.8 | – | – | – | – | 2026-08 | community | – | source |
| GB10 | Nemotron 3 Nano 30B-A3B 30B | NVFP4 | llama.cpp (CUDA) | 350.8 | – | – | – | – | 2026-08 | community | – | source |
| RTX PRO 6000 | Nemotron 3 Nano 30B-A3B 30B | NVFP4 | llama.cpp (CUDA) | 333.2 | – | – | – | – | 2026-08 | community | – | source |
| RTX PRO 6000 | Nemotron 3 Nano 30B-A3B 30B | NVFP4 | llama.cpp (CUDA) | 332.0 | – | – | – | – | 2026-08 | community | – | source |
| GB10 | Nemotron 3 Nano 30B-A3B 30B | NVFP4 | llama.cpp (CUDA) | 292.5 | – | – | – | – | 2026-08 | community | – | source |
| GB10 | Nemotron 3 Nano 30B-A3B 30B | NVFP4 | llama.cpp (CUDA) | 214.8 | – | – | – | – | 2026-08 | community | – | source |
| GB10 | Nemotron 3 Nano 30B-A3B 30B | NVFP4 | llama.cpp (CUDA) | 202.6 | – | – | – | – | 2026-08 | community | – | source |
| GB10 | Nemotron 3 Nano 30B-A3B 30B | NVFP4 | llama.cpp (CUDA) | 152.4 | – | – | – | – | 2026-08 | community | – | source |
| GB10 | Nemotron 3 Nano 30B-A3B 30B | NVFP4 | llama.cpp (CUDA) | 67.7 | – | – | – | – | 2026-08 | community | – | source |
| GB10 | Nemotron 3 Nano 30B-A3B 30B | NVFP4 | llama.cpp (CUDA) | 67.5 | – | – | – | – | 2026-08 | community | – | source |
| M1 Max (64 GB) | Nemotron 3 Nano 30B-A3B | Q4_K_XL | llama.cpp | 43.7 | 136.9 | – | – | 4096 | – | sourced | – | source |