can-i-run-this-llm

Can I run this LLM?

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

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

Yes — it runs great.

Best fit: Laguna S 2.1 (MoE) at Q8_0 · 125.0 GB · 233–349 tok/s on a AMD Instinct MI355X (288GB).

Every quantization on this machine

QuantSizeSpeedFit
Q3_K_M54.0 GB287–431 tok/sRuns great
Q4_K_M73.1 GB270–405 tok/sRuns great
Q5_K_M87.9 GB258–387 tok/sRuns great
Q6_K97.9 GB251–376 tok/sRuns great
Q8_0125.0 GB233–349 tok/sRuns great
FP16235.2 GB180–269 tok/sTight / slow

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