can-i-run-this-llm

Can I run this LLM?

Can a MacBook Pro M3 Max (36GB) run Laguna XS 2.1 (MoE)?

Laguna · openmdw-1.1 · estimated for a 36.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Laguna XS 2.1 (MoE) at Q4_K_M · 20.6 GB · 55–82 tok/s on a MacBook Pro M3 Max (36GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K12.2 GB69–103 tok/sRuns great
Q3_K_M15.6 GB62–93 tok/sRuns great
Q4_K_M20.6 GB55–82 tok/sRuns great
Q5_K_M24.0 GB51–76 tok/sWon't fit
Q6_K29.0 GB45–68 tok/sWon't fit
Q8_035.6 GB40–60 tok/sWon't fit
FP1666.9 GB26–39 tok/sWon't fit

Ran Laguna XS 2.1 (MoE) on a MacBook Pro M3 Max (36GB)? Add your real numbers →