can-i-run-this-llm

Can I run this LLM?

Can a MacBook Pro M5 Max (36GB) run Qwen3 30B-A3B (MoE)?

Qwen · Apache 2.0 · estimated for a 36.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Qwen3 30B-A3B (MoE) at Q4_K_M · 18.6 GB · 77–115 tok/s on a MacBook Pro M5 Max (36GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K11.3 GB94–140 tok/sRuns great
Q3_K_M14.7 GB85–127 tok/sRuns great
Q4_K_M18.6 GB77–115 tok/sRuns great
Q5_K_M21.7 GB71–107 tok/sTight / slow
Q6_K25.1 GB66–100 tok/sWon't fit
Q8_032.5 GB57–86 tok/sWon't fit
FP1661.1 GB38–57 tok/sWon't fit

Ran Qwen3 30B-A3B (MoE) on a MacBook Pro M5 Max (36GB)? Add your real numbers →