can-i-run-this-llm

Can I run this LLM?

Can a Mac Studio M3 Ultra (96GB) run Laguna S 2.1 (MoE)?

Laguna · openmdw-1.1 · estimated for a 96.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Laguna S 2.1 (MoE) at Q3_K_M · 54.0 GB · 77–116 tok/s on a Mac Studio M3 Ultra (96GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K39.7 GB89–134 tok/sRuns great
Q3_K_M54.0 GB77–116 tok/sRuns great
Q4_K_M73.1 GB65–98 tok/sWon't fit
Q5_K_M87.9 GB58–87 tok/sWon't fit
Q6_K97.9 GB54–82 tok/sWon't fit
Q8_0125.0 GB46–69 tok/sWon't fit
FP16235.2 GB28–42 tok/sWon't fit

Ran Laguna S 2.1 (MoE) on a Mac Studio M3 Ultra (96GB)? Add your real numbers →