can-i-run-this-llm

Can I run this LLM?

Can a Mac Studio M5 Ultra (256GB) run Ornith 1.0 35B (MoE)?

Ornith · MIT · estimated for a 256.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Ornith 1.0 35B (MoE) at FP16 · 69.4 GB · 76–114 tok/s on a Mac Studio M5 Ultra (256GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K12.3 GB139–208 tok/sRuns great
Q3_K_M16.7 GB130–196 tok/sRuns great
Q4_K_M22.1 GB121–182 tok/sRuns great
Q5_K_M26.5 GB115–173 tok/sRuns great
Q6_K29.3 GB111–167 tok/sRuns great
Q8_036.9 GB102–153 tok/sRuns great
FP1669.4 GB76–114 tok/sRuns great

Ran Ornith 1.0 35B (MoE) on a Mac Studio M5 Ultra (256GB)? Add your real numbers →