community pool / model answer
NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4
chat · nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4
582.5 tok/s · model median · 3 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| RTX 5090 32GB | 4-bit | 582.5 tok/s | measured | 322 | - GB | 2,048 | vllm |
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.