can-i-run-this-llm

Can I run this LLM?

Can a MacBook Air/Pro M4 (16GB) run Qwen3 8B?

Qwen · Apache 2.0 · estimated for a 16.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Qwen3 8B at Q4_K_M · 5.0 GB · 13–20 tok/s on a MacBook Air/Pro M4 (16GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K3.3 GB19–28 tok/sRuns great
Q3_K_M4.1 GB16–23 tok/sRuns great
Q4_K_M5.0 GB13–20 tok/sRuns great
Q5_K_M5.9 GB12–18 tok/sTight / slow
Q6_K6.7 GB10–16 tok/sTight / slow
Q8_08.7 GB8–12 tok/sTight / slow
FP1616.4 GB5–7 tok/sWon't fit

Ran Qwen3 8B on a MacBook Air/Pro M4 (16GB)? Add your real numbers →