community pool / model answer

Qwen3.8-27B-MTP-GGUF

chat · Jackrong/Qwen3.8-27B-MTP-GGUF

26.7 tok/s · model median · 35 runs in the model record.

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
CMP 170HX 64GB4-bit58 tok/smeasured-- GB16,384llama.cpp
CMP 170HX 64GB8-bit26 tok/smeasured1,718- GB132,352llama.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.