can-i-run-this-llm

Can I run this LLM?

Can a Mac Studio M2 Ultra (192GB) run Ornith 1.5 35B-A3B (MoE)?

Ornith · MIT · estimated for a 192.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Ornith 1.5 35B-A3B (MoE) at FP16 · 71.1 GB · 58–88 tok/s on a Mac Studio M2 Ultra (192GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K13.1 GB124–186 tok/sRuns great
Q3_K_M16.7 GB116–174 tok/sRuns great
Q4_K_M21.9 GB106–159 tok/sRuns great
Q5_K_M25.5 GB100–150 tok/sRuns great
Q6_K30.5 GB93–139 tok/sRuns great
Q8_037.8 GB84–126 tok/sRuns great
FP1671.1 GB58–88 tok/sRuns great

Ran Ornith 1.5 35B-A3B (MoE) on a Mac Studio M2 Ultra (192GB)? Add your real numbers →