can-i-run-this-llm

Can I run this LLM?

Can a MacBook Pro M5 Max (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 · 94–141 tok/s on a MacBook Pro M5 Max (36GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K13.1 GB103–155 tok/sRuns great
Q3_K_M16.7 GB94–141 tok/sRuns great
Q4_K_M21.9 GB83–124 tok/sTight / slow
Q5_K_M25.5 GB77–115 tok/sWon't fit
Q6_K30.5 GB69–104 tok/sWon't fit
Q8_037.8 GB61–91 tok/sWon't fit
FP1671.1 GB39–59 tok/sWon't fit

Ran Ornith 1.5 35B-A3B (MoE) on a MacBook Pro M5 Max (36GB)? Add your real numbers →