can-i-run-this-llm

Can I run this LLM?

Can a MacBook Pro M2 Max (96GB) run Qwen3 32B?

Qwen · Apache 2.0 · estimated for a 96.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Qwen3 32B at Q4_K_M · 19.8 GB · 12–18 tok/s on a MacBook Pro M2 Max (96GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K12.3 GB18–27 tok/sRuns great
Q3_K_M16.0 GB14–22 tok/sRuns great
Q4_K_M19.8 GB12–18 tok/sRuns great
Q5_K_M23.2 GB10–16 tok/sTight / slow
Q6_K26.9 GB9–14 tok/sTight / slow
Q8_034.8 GB7–11 tok/sTight / slow
FP1665.5 GB4–6 tok/sWon't fit

Ran Qwen3 32B on a MacBook Pro M2 Max (96GB)? Add your real numbers →