can-i-run-this-llm

Can I run this LLM?

Can a MacBook Pro M5 Max (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 · 73.1 GB · 54–81 tok/s on a MacBook Pro M5 Max (128GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K39.7 GB77–115 tok/sRuns great
Q3_K_M54.0 GB65–98 tok/sRuns great
Q4_K_M73.1 GB54–81 tok/sRuns great
Q5_K_M87.9 GB48–72 tok/sTight / slow
Q6_K97.9 GB44–66 tok/sWon't fit
Q8_0125.0 GB37–55 tok/sWon't fit
FP16235.2 GB22–33 tok/sWon't fit

Ran Laguna S 2.1 (MoE) on a MacBook Pro M5 Max (128GB)? Add your real numbers →