can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA DGX Spark (GB10, 128GB) run Laguna S 2.1 (MoE)?

Laguna · openmdw-1.1 · estimated for a 128.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Laguna S 2.1 (MoE) at Q4_K_M · 71.3 GB · 27–41 tok/s on a NVIDIA DGX Spark (GB10, 128GB).

Every quantization on this machine

QuantSizeSpeedFit
Q3_K_M50.7 GB35–52 tok/sRuns great
Q4_K_M71.3 GB27–41 tok/sRuns great
Q5_K_M83.8 GB24–36 tok/sTight / slow
Q6_K97.0 GB22–33 tok/sWon't fit
Q8_0124.9 GB18–27 tok/sWon't fit
FP16235.1 GB10–15 tok/sWon't fit

Ran Laguna S 2.1 (MoE) on a NVIDIA DGX Spark (GB10, 128GB)? Add your real numbers →