can-i-run-this-llm

Can I run this LLM?

Can a MacBook Pro M5 Pro (64GB) run Laguna S 2.1 (MoE)?

Laguna · openmdw-1.1 · estimated for a 64.0 GB machine at 4K context.

Yes, but it's tight.

Best fit: Laguna S 2.1 (MoE) at Q2_K · 39.7 GB · 50–74 tok/s on a MacBook Pro M5 Pro (64GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K39.7 GB50–74 tok/sTight / slow
Q3_K_M54.0 GB40–60 tok/sWon't fit
Q4_K_M73.1 GB32–48 tok/sWon't fit
Q5_K_M87.9 GB28–42 tok/sWon't fit
Q6_K97.9 GB25–38 tok/sWon't fit
Q8_0125.0 GB21–31 tok/sWon't fit
FP16235.2 GB12–18 tok/sWon't fit

Ran Laguna S 2.1 (MoE) on a MacBook Pro M5 Pro (64GB)? Add your real numbers →