can-i-run-this-llm

Can I run this LLM?

Can a MacBook Air/Pro M5 (24GB) run Qwen3.5 9B?

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

Yes — it runs great.

Best fit: Qwen3.5 9B at Q6_K · 7.5 GB · 12–18 tok/s on a MacBook Air/Pro M5 (24GB).

Every quantization on this machine

QuantSizeSpeedFit
Q3_K_M4.7 GB18–27 tok/sRuns great
Q4_K_M5.7 GB15–23 tok/sRuns great
Q5_K_M6.6 GB13–20 tok/sRuns great
Q6_K7.5 GB12–18 tok/sRuns great
Q8_09.5 GB10–15 tok/sTight / slow
FP1617.9 GB5–8 tok/sWon't fit

Ran Qwen3.5 9B on a MacBook Air/Pro M5 (24GB)? Add your real numbers →