community pool / model answer

Qwen3.5-9B-4bit

chat · mlx-community/Qwen3.5-9B-4bit

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

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
M2 Pro 16GB4-bit33 tok/sreported1,400- 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.