can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA RTX 5090 (32GB) run Laguna XS 2.1 (MoE)?

Laguna · openmdw-1.1 · estimated for a 32.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Laguna XS 2.1 (MoE) at Q5_K_M · 24.0 GB · 206–309 tok/s on a NVIDIA RTX 5090 (32GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K12.2 GB247–370 tok/sRuns great
Q3_K_M15.6 GB233–350 tok/sRuns great
Q4_K_M20.6 GB216–324 tok/sRuns great
Q5_K_M24.0 GB206–309 tok/sRuns great
Q6_K29.0 GB192–289 tok/sWon't fit
Q8_035.6 GB177–266 tok/sWon't fit
FP1666.9 GB129–193 tok/sWon't fit

Ran Laguna XS 2.1 (MoE) on a NVIDIA RTX 5090 (32GB)? Add your real numbers →