community pool / model answer

Hy-MT2-7B-GGUF

chat · tencent/Hy-MT2-7B-GGUF

37.6 tok/s · model median · 3 runs in the model record.

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
RTX 3060 12GB4-bit37.6 tok/smeasured1,282- GB4,096llama.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.