community pool / model answer

Hy-MT2-30B-A3B-FP8

chat · tencent/Hy-MT2-30B-A3B-FP8

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

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
CMP 170HX 64GB ×28-bit86.5 tok/smeasured898114.8 GB32,768vllm

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.