community pool / model answer
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
chat · nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
285.6 tok/s · model median · 3 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| RTX 3060 + RTX 2080 20GB | 4-bit | 117 tok/s | reported | - | 17 GB | 2,048 | llama.cpp |
| RTX 5090 32GB | 4-bit | 299.4 tok/s | reported | 123 | 21.7 GB | 8,192 | llama.cpp, ollama |
Context tested
The table above is the tested context for each exact rig and quantization cell. Empty fields remain empty rather than being filled with an estimate.