community pool / model answer

Mistral-Medium-3.5-128B

chat · mistralai/Mistral-Medium-3.5-128B

6.5 tok/s · model median · 9 runs in the model record.

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
Radeon AI Pro R9700 32GB ×34-bit6.4 tok/smeasured2,885- GB16,384llama.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.