can-i-run-this-llm

Can I run this LLM?

Can a MacBook Pro M5 Max (128GB) run Ornith 1.0 35B (MoE)?

Ornith · MIT · estimated for a 128.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Ornith 1.0 35B (MoE) at FP16 · 69.4 GB · 49–73 tok/s on a MacBook Pro M5 Max (128GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K12.3 GB116–175 tok/sRuns great
Q3_K_M16.7 GB105–158 tok/sRuns great
Q4_K_M22.1 GB94–141 tok/sRuns great
Q5_K_M26.5 GB87–130 tok/sRuns great
Q6_K29.3 GB82–123 tok/sRuns great
Q8_036.9 GB73–109 tok/sRuns great
FP1669.4 GB49–73 tok/sRuns great

Ran Ornith 1.0 35B (MoE) on a MacBook Pro M5 Max (128GB)? Add your real numbers →