community pool / model answer

Qwen3.5-4B-MLX-8bit

chat · mlx-community/Qwen3.5-4B-MLX-8bit

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

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
M4 Pro 48GB8-bit47.8 tok/sreported-6.2 GB2,176mlx

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.