can-i-run-this-llm

Can I run this LLM?

Can a MacBook Air/Pro M1 (16GB) run Qwen3 14B?

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

Yes, but it's tight.

Best fit: Qwen3 14B at Q2_K · 5.8 GB · 7–10 tok/s on a MacBook Air/Pro M1 (16GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K5.8 GB7–10 tok/sTight / slow
Q3_K_M7.3 GB6–8 tok/sTight / slow
Q4_K_M9.0 GB5–7 tok/sTight / slow
Q5_K_M10.5 GB4–6 tok/sWon't fit
Q6_K12.1 GB4–5 tok/sWon't fit
Q8_015.7 GB3–4 tok/sWon't fit
FP1629.5 GB2–2 tok/sWon't fit

Ran Qwen3 14B on a MacBook Air/Pro M1 (16GB)? Add your real numbers →