community pool / model answer

Nemotron-3-Nano-Omni-30B-A3B-Reasoning-NVFP4

chat · nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-NVFP4

377.2 tok/s · model median · 1 runs in the model record.

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
GB10 Grace Blackwell 128GB4-bit71.6 tok/sreported1,808- GB10,000vllm

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.