community pool / model answer

Hunyuan-MT-7B

chat · tencent/Hunyuan-MT-7B

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

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
RTX 3090 24GB4-bit74.3 tok/smeasured2,3800 GB131,072llama.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.