can-i-run-this-llm

Can I run this LLM?

Can a AMD Instinct MI300X (192GB) run Laguna S 2.1 (MoE)?

Laguna · openmdw-1.1 · estimated for a 192.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Laguna S 2.1 (MoE) at Q8_0 · 124.9 GB · 196–294 tok/s on a AMD Instinct MI300X (192GB).

Every quantization on this machine

QuantSizeSpeedFit
Q3_K_M50.7 GB262–393 tok/sRuns great
Q4_K_M71.3 GB240–360 tok/sRuns great
Q5_K_M83.8 GB228–342 tok/sRuns great
Q6_K97.0 GB217–325 tok/sRuns great
Q8_0124.9 GB196–294 tok/sRuns great
FP16235.1 GB142–214 tok/sWon't fit

Ran Laguna S 2.1 (MoE) on a AMD Instinct MI300X (192GB)? Add your real numbers →