can-i-run-this-llm

Can I run this LLM?

Can a Mac Studio M1 Ultra (64GB) run Laguna XS 2.1 (MoE)?

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

Yes — it runs great.

Best fit: Laguna XS 2.1 (MoE) at Q8_0 · 35.6 GB · 77–116 tok/s on a Mac Studio M1 Ultra (64GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K12.2 GB110–165 tok/sRuns great
Q3_K_M15.6 GB104–155 tok/sRuns great
Q4_K_M20.6 GB95–143 tok/sRuns great
Q5_K_M24.0 GB90–136 tok/sRuns great
Q6_K29.0 GB84–126 tok/sRuns great
Q8_035.6 GB77–116 tok/sRuns great
FP1666.9 GB55–82 tok/sWon't fit

Ran Laguna XS 2.1 (MoE) on a Mac Studio M1 Ultra (64GB)? Add your real numbers →