community pool / model answer

MiniMax-M2.7-NVFP4

chat · nvidia/MiniMax-M2.7-NVFP4

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

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
RTX PRO 6000 98GB ×24-bit92.8 tok/sreported66- GB2,048sglang

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.