community pool / model answer

Hy-MT2-7B

chat · tencent/Hy-MT2-7B

31 tok/s · model median · 7 runs in the model record.

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
RTX 3090 24GB4-bit98.1 tok/sreported-- GB1,024llama.cpp
RX 570 4GB ×24-bit29.3 tok/smeasured75- GB2,048llama.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.