can-i-run-this-llm

Can I run this LLM?

Can a AMD Instinct MI355X (288GB) run Laguna XS 2.1 (MoE)?

Laguna · openmdw-1.1 · estimated for a 288.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Laguna XS 2.1 (MoE) at FP16 · 66.9 GB · 259–389 tok/s on a AMD Instinct MI355X (288GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K12.2 GB331–496 tok/sRuns great
Q3_K_M15.6 GB325–488 tok/sRuns great
Q4_K_M20.6 GB317–476 tok/sRuns great
Q5_K_M24.0 GB312–468 tok/sRuns great
Q6_K29.0 GB305–457 tok/sRuns great
Q8_035.6 GB296–444 tok/sRuns great
FP1666.9 GB259–389 tok/sRuns great

Ran Laguna XS 2.1 (MoE) on a AMD Instinct MI355X (288GB)? Add your real numbers →