can-i-run-this-llm

Can I run this LLM?

Can a Mac Studio M5 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 · 94–142 tok/s on a Mac Studio M5 Ultra (96GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K39.7 GB106–159 tok/sRuns great
Q3_K_M54.0 GB94–142 tok/sRuns great
Q4_K_M73.1 GB82–123 tok/sWon't fit
Q5_K_M87.9 GB75–112 tok/sWon't fit
Q6_K97.9 GB70–106 tok/sWon't fit
Q8_0125.0 GB61–91 tok/sWon't fit
FP16235.2 GB39–59 tok/sWon't fit

Ran Laguna S 2.1 (MoE) on a Mac Studio M5 Ultra (96GB)? Add your real numbers →