can-i-run-this-llm

Can I run this LLM?

Can a MacBook Pro M5 Max (128GB) run DeepSeek-R1-Distill 32B?

DeepSeek · Apache 2.0 · estimated for a 128.0 GB machine at 4K context.

Yes — it runs great.

Best fit: DeepSeek-R1-Distill 32B at Q6_K · 26.9 GB · 14–20 tok/s on a MacBook Pro M5 Max (128GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K12.3 GB26–39 tok/sRuns great
Q3_K_M15.9 GB21–32 tok/sRuns great
Q4_K_M19.9 GB18–27 tok/sRuns great
Q5_K_M23.3 GB15–23 tok/sRuns great
Q6_K26.9 GB14–20 tok/sRuns great
Q8_034.8 GB11–16 tok/sTight / slow
FP1665.5 GB6–9 tok/sTight / slow

Ran DeepSeek-R1-Distill 32B on a MacBook Pro M5 Max (128GB)? Add your real numbers →