community pool / model answer

Qwen3.8-27B-oQ8-mtp

chat · mcsplain/Qwen3.8-27B-oQ8-mtp

39.6 tok/s · model median · 1 runs in the model record.

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
M5 Max 128GB8-bit39.6 tok/sreported1,27028.8 GB4,096mlx

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.