community pool / model answer

MiniMax-M2.5-REAP-139B-A10B

chat · cerebras/MiniMax-M2.5-REAP-139B-A10B

32.3 tok/s · model median · 8 runs in the model record.

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
Radeon AI Pro R9700 32GB ×34-bit30.4 tok/smeasured4,212- GB921llama.cpp
RTX PRO 6000 Blackwell 96GB4-bit97.2 tok/smeasured1,094- GB15,904llama.cpp

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.