can-i-run-this-llm

Can I run this LLM?

Can a MacBook Air/Pro M5 (24GB) run Qwen3.8 27B?

Qwen · Apache 2.0 · estimated for a 24.0 GB machine at 4K context.

Yes, but it's tight.

Best fit: Qwen3.8 27B at Q3_K_M · 13.8 GB · 7–10 tok/s on a MacBook Air/Pro M5 (24GB).

Every quantization on this machine

QuantSizeSpeedFit
Q3_K_M13.8 GB7–10 tok/sTight / slow
Q4_K_M17.1 GB5–8 tok/sWon't fit
Q5_K_M19.8 GB5–7 tok/sWon't fit
Q6_K22.9 GB4–6 tok/sWon't fit
Q8_029.1 GB3–5 tok/sWon't fit
FP1654.7 GB2–3 tok/sWon't fit

Ran Qwen3.8 27B on a MacBook Air/Pro M5 (24GB)? Add your real numbers →