community pool / model answer

Qwen3.6-35B-A3B-UD-Q8_K_XL-mlx

chat · Brooooooklyn/Qwen3.6-35B-A3B-UD-Q8_K_XL-mlx

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

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
M4 Max 64GB8-bit83.4 tok/sreported10622 GB262,144mlx

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.