can-i-run-this-llm

Can I run this LLM?

Can a MacBook Air/Pro M5 (32GB) run Qwen3 30B-A3B (MoE)?

Qwen · Apache 2.0 · estimated for a 32.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Qwen3 30B-A3B (MoE) at Q4_K_M · 18.6 GB · 37–55 tok/s on a MacBook Air/Pro M5 (32GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K11.3 GB49–73 tok/sRuns great
Q3_K_M14.7 GB42–63 tok/sRuns great
Q4_K_M18.6 GB37–55 tok/sRuns great
Q5_K_M21.7 GB33–49 tok/sWon't fit
Q6_K25.1 GB30–45 tok/sWon't fit
Q8_032.5 GB25–37 tok/sWon't fit
FP1661.1 GB15–22 tok/sWon't fit

Ran Qwen3 30B-A3B (MoE) on a MacBook Air/Pro M5 (32GB)? Add your real numbers →