can-i-run-this-llm

Can I run this LLM?

Can a MacBook Pro M1 Pro (32GB) run Phi-4 14B?

Phi · MIT · estimated for a 32.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Phi-4 14B at Q4_K_M · 8.9 GB · 13–19 tok/s on a MacBook Pro M1 Pro (32GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K5.6 GB19–28 tok/sRuns great
Q3_K_M7.2 GB15–23 tok/sRuns great
Q4_K_M8.9 GB13–19 tok/sRuns great
Q5_K_M10.4 GB11–17 tok/sTight / slow
Q6_K12.0 GB10–15 tok/sTight / slow
Q8_015.6 GB8–12 tok/sTight / slow
FP1629.3 GB4–7 tok/sWon't fit

Ran Phi-4 14B on a MacBook Pro M1 Pro (32GB)? Add your real numbers →