can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA RTX 5080 (16GB) run Laguna XS 2.1 (MoE)?

Laguna · openmdw-1.1 · estimated for a 16.0 GB machine at 4K context.

Yes, but it's tight.

Best fit: Laguna XS 2.1 (MoE) at Q2_K · 12.2 GB · 192–288 tok/s on a NVIDIA RTX 5080 (16GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K12.2 GB192–288 tok/sTight / slow
Q3_K_M15.6 GB177–266 tok/sWon't fit
Q4_K_M20.6 GB159–239 tok/sWon't fit
Q5_K_M24.0 GB149–224 tok/sWon't fit
Q6_K29.0 GB136–204 tok/sWon't fit
Q8_035.6 GB122–184 tok/sWon't fit
FP1666.9 GB82–124 tok/sWon't fit

Ran Laguna XS 2.1 (MoE) on a NVIDIA RTX 5080 (16GB)? Add your real numbers →