can-i-run-this-llm

Can I run this LLM?

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

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

Yes — it runs great.

Best fit: Laguna XS 2.1 (MoE) at FP16 · 66.9 GB · 226–339 tok/s on a AMD Instinct MI300X (192GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K12.2 GB315–472 tok/sRuns great
Q3_K_M15.6 GB307–461 tok/sRuns great
Q4_K_M20.6 GB297–445 tok/sRuns great
Q5_K_M24.0 GB290–435 tok/sRuns great
Q6_K29.0 GB281–421 tok/sRuns great
Q8_035.6 GB269–404 tok/sRuns great
FP1666.9 GB226–339 tok/sRuns great

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