can-i-run-this-llm

Can I run this LLM?

Can a MacBook Pro M4 Pro (48GB) run Ornith 1.0 35B (MoE)?

Ornith · MIT · estimated for a 48.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Ornith 1.0 35B (MoE) at Q5_K_M · 26.5 GB · 50–75 tok/s on a MacBook Pro M4 Pro (48GB).

Every quantization on this machine

QuantSizeSpeedFit
Q3_K_M16.7 GB65–97 tok/sRuns great
Q4_K_M22.1 GB55–83 tok/sRuns great
Q5_K_M26.5 GB50–75 tok/sRuns great
Q6_K29.3 GB47–70 tok/sTight / slow
Q8_036.9 GB40–60 tok/sWon't fit
FP1669.4 GB25–37 tok/sWon't fit

Ran Ornith 1.0 35B (MoE) on a MacBook Pro M4 Pro (48GB)? Add your real numbers →