can-i-run-this-llm

Can I run this LLM?

Can a MacBook Air/Pro M1 (16GB) run Phi-4 14B?

Phi · MIT · estimated for a 16.0 GB machine at 4K context.

Yes, but it's tight.

Best fit: Phi-4 14B at Q2_K · 5.6 GB · 7–10 tok/s on a MacBook Air/Pro M1 (16GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K5.6 GB7–10 tok/sTight / slow
Q3_K_M7.2 GB6–8 tok/sTight / slow
Q4_K_M8.9 GB5–7 tok/sTight / slow
Q5_K_M10.4 GB4–6 tok/sWon't fit
Q6_K12.0 GB3–5 tok/sWon't fit
Q8_015.6 GB3–4 tok/sWon't fit
FP1629.3 GB2–2 tok/sWon't fit

Ran Phi-4 14B on a MacBook Air/Pro M1 (16GB)? Add your real numbers →