can-i-run-this-llm

Can I run this LLM?

Can a MacBook Pro M5 Max (36GB) run DeepSeek-R1-Distill 14B?

DeepSeek · Apache 2.0 · estimated for a 36.0 GB machine at 4K context.

Yes — it runs great.

Best fit: DeepSeek-R1-Distill 14B at Q8_0 · 15.7 GB · 17–25 tok/s on a MacBook Pro M5 Max (36GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K5.8 GB37–56 tok/sRuns great
Q3_K_M7.3 GB31–47 tok/sRuns great
Q4_K_M9.0 GB27–40 tok/sRuns great
Q5_K_M10.5 GB24–35 tok/sRuns great
Q6_K12.1 GB21–32 tok/sRuns great
Q8_015.7 GB17–25 tok/sRuns great
FP1629.6 GB10–14 tok/sWon't fit

Ran DeepSeek-R1-Distill 14B on a MacBook Pro M5 Max (36GB)? Add your real numbers →