can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA H200 (141GB) run Laguna S 2.1 (MoE)?

Laguna · openmdw-1.1 · estimated for a 141.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Laguna S 2.1 (MoE) at Q6_K · 97.9 GB · 207–310 tok/s on a NVIDIA H200 (141GB).

Every quantization on this machine

QuantSizeSpeedFit
Q3_K_M54.0 GB251–376 tok/sRuns great
Q4_K_M73.1 GB230–344 tok/sRuns great
Q5_K_M87.9 GB216–323 tok/sRuns great
Q6_K97.9 GB207–310 tok/sRuns great
Q8_0125.0 GB187–280 tok/sTight / slow
FP16235.2 GB134–201 tok/sWon't fit

Ran Laguna S 2.1 (MoE) on a NVIDIA H200 (141GB)? Add your real numbers →