community pool / model answer

NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-NVFP4

chat · nvidia/NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-NVFP4

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

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
GB10 Grace Blackwell 128GB4-bit38.7 tok/sreported-- GB262,144vllm

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.