can-i-run-this-llm

Can I run this LLM?

Can a AMD Ryzen AI Max+ 395 “Strix Halo” (128GB) run Laguna XS 2.1 (MoE)?

Laguna · openmdw-1.1 · estimated for a 128.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Laguna XS 2.1 (MoE) at FP16 · 66.9 GB · 22–34 tok/s on a AMD Ryzen AI Max+ 395 “Strix Halo” (128GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K12.2 GB62–94 tok/sRuns great
Q3_K_M15.6 GB56–84 tok/sRuns great
Q4_K_M20.6 GB49–74 tok/sRuns great
Q5_K_M24.0 GB45–68 tok/sRuns great
Q6_K29.0 GB40–61 tok/sRuns great
Q8_035.6 GB35–53 tok/sRuns great
FP1666.9 GB22–34 tok/sRuns great

Ran Laguna XS 2.1 (MoE) on a AMD Ryzen AI Max+ 395 “Strix Halo” (128GB)? Add your real numbers →