community-verified · measured pool data

Can the M4 Pro 48GB run Qwen3.5-9B-MLX-8bit?

Yes — community-measured at 26.4 tok/s (2 runs at 8-bit).

Verified single-stream runs on the M4 Pro 48GB from the localmaxxing public pool. Every number on this page is measured — nothing here is estimated.

Quantization Median tok/s TTFT (ms) Peak VRAM Max context tested Engines
8-bit 26.4 1418 11.2 GB 249,088 lmstudio, mlx
Go deeper
I have a goal — find models that fit my use case → I have hardware — browse everything my rig can run → All machine × model answer pages →