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 rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
RTX 5090 32GB4-bit582.5 tok/smeasured322- GB2,048vllm

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.