can-i-run-this-llm

Can I run this LLM?

Can a MacBook Pro M3 Pro (36GB) run Ornith 1.5 35B-A3B (MoE)?

Ornith · MIT · estimated for a 36.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Ornith 1.5 35B-A3B (MoE) at Q3_K_M · 16.7 GB · 48–73 tok/s on a MacBook Pro M3 Pro (36GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K13.1 GB57–85 tok/sRuns great
Q3_K_M16.7 GB48–73 tok/sRuns great
Q4_K_M21.9 GB40–60 tok/sTight / slow
Q5_K_M25.5 GB36–54 tok/sWon't fit
Q6_K30.5 GB31–47 tok/sWon't fit
Q8_037.8 GB26–39 tok/sWon't fit
FP1671.1 GB15–23 tok/sWon't fit

Ran Ornith 1.5 35B-A3B (MoE) on a MacBook Pro M3 Pro (36GB)? Add your real numbers →