can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA L40S (48GB) run Laguna XS 2.1 (MoE)?

Laguna · openmdw-1.1 · estimated for a 48.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Laguna XS 2.1 (MoE) at Q8_0 · 35.6 GB · 114–171 tok/s on a NVIDIA L40S (48GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K12.2 GB182–273 tok/sRuns great
Q3_K_M15.6 GB168–251 tok/sRuns great
Q4_K_M20.6 GB150–225 tok/sRuns great
Q5_K_M24.0 GB140–210 tok/sRuns great
Q6_K29.0 GB127–191 tok/sRuns great
Q8_035.6 GB114–171 tok/sRuns great
FP1666.9 GB76–114 tok/sWon't fit

Ran Laguna XS 2.1 (MoE) on a NVIDIA L40S (48GB)? Add your real numbers →