can-i-run-this-llm

Can I run this LLM?

Can a MacBook Pro M5 Pro (24GB) run Ornith 1.5 35B-A3B (MoE)?

Ornith · MIT · estimated for a 24.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Ornith 1.5 35B-A3B (MoE) at Q2_K · 13.1 GB · 86–129 tok/s on a MacBook Pro M5 Pro (24GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K13.1 GB86–129 tok/sRuns great
Q3_K_M16.7 GB76–115 tok/sWon't fit
Q4_K_M21.9 GB66–99 tok/sWon't fit
Q5_K_M25.5 GB60–90 tok/sWon't fit
Q6_K30.5 GB53–80 tok/sWon't fit
Q8_037.8 GB46–69 tok/sWon't fit
FP1671.1 GB28–43 tok/sWon't fit

Ran Ornith 1.5 35B-A3B (MoE) on a MacBook Pro M5 Pro (24GB)? Add your real numbers →