community pool / model answer

Qwen3.6-27B-UD-MLX-4bit

chat · unsloth/Qwen3.6-27B-UD-MLX-4bit

18.4 tok/s · model median · 2 runs in the model record.

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
M4 Max 64GB4-bit18.4 tok/sreported67625.9 GB6,128mlx

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.