Can I run this LLM?

Can a MacBook Pro M4 Max (48GB) run Qwen3 Coder Next 80B-A3B (MoE)?

Qwen · Apache 2.0 · estimated for a 48.0 GB machine at 4K context.

Yes, but it's tight.

Best fit: Qwen3 Coder Next 80B-A3B (MoE) at Q2_K · 29.2 GB · 101–151 tok/s on a MacBook Pro M4 Max (48GB).

Every quantization on this machine

Quant	Size	Speed	Fit
Q2_K	29.2 GB	101–151 tok/s	Tight / slow
Q3_K_M	38.3 GB	92–138 tok/s	Won't fit
Q4_K_M	49.3 GB	84–125 tok/s	Won't fit
Q5_K_M	59.2 GB	77–116 tok/s	Won't fit
Q6_K	65.8 GB	73–110 tok/s	Won't fit
Q8_0	84.8 GB	64–96 tok/s	Won't fit
FP16	159.5 GB	43–65 tok/s	Won't fit

Ran Qwen3 Coder Next 80B-A3B (MoE) on a MacBook Pro M4 Max (48GB)? Add your real numbers →