can-i-run-this-llm

Can I run this LLM?

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

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

Yes — it runs great.

Best fit: Laguna XS 2.1 (MoE) at FP16 · 66.9 GB · 24–36 tok/s on a NVIDIA DGX Spark (GB10, 128GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K12.2 GB65–97 tok/sRuns great
Q3_K_M15.6 GB59–88 tok/sRuns great
Q4_K_M20.6 GB51–77 tok/sRuns great
Q5_K_M24.0 GB47–71 tok/sRuns great
Q6_K29.0 GB42–64 tok/sRuns great
Q8_035.6 GB37–56 tok/sRuns great
FP1666.9 GB24–36 tok/sRuns great

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