can-i-run-this-llm

Can I run this LLM?

Can a Mac Studio M1 Ultra (128GB) run Laguna S 2.1 (MoE)?

Laguna · openmdw-1.1 · estimated for a 128.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Laguna S 2.1 (MoE) at Q4_K_M · 71.3 GB · 61–92 tok/s on a Mac Studio M1 Ultra (128GB).

Every quantization on this machine

QuantSizeSpeedFit
Q3_K_M50.7 GB73–109 tok/sRuns great
Q4_K_M71.3 GB61–92 tok/sRuns great
Q5_K_M83.8 GB56–84 tok/sTight / slow
Q6_K97.0 GB51–77 tok/sWon't fit
Q8_0124.9 GB43–65 tok/sWon't fit
FP16235.1 GB27–41 tok/sWon't fit

Ran Laguna S 2.1 (MoE) on a Mac Studio M1 Ultra (128GB)? Add your real numbers →