community pool / model answer

GLM-5.2-MLX-mixed-3_6bit

chat · pipenetwork/GLM-5.2-MLX-mixed-3_6bit

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

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
M3 Ultra 512GB3-bit14.8 tok/sreported80,062- GB8,192mlx

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.