Can I run this LLM?
Can a NVIDIA H200 (141GB) run Laguna XS 2.1 (MoE)?
Laguna · openmdw-1.1 · estimated for a 141.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Laguna XS 2.1 (MoE) at FP16 · 66.9 GB · 217–326 tok/s on a NVIDIA H200 (141GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 12.2 GB | 310–466 tok/s | Runs great |
| Q3_K_M | 15.6 GB | 302–453 tok/s | Runs great |
| Q4_K_M | 20.6 GB | 291–437 tok/s | Runs great |
| Q5_K_M | 24.0 GB | 284–426 tok/s | Runs great |
| Q6_K | 29.0 GB | 274–411 tok/s | Runs great |
| Q8_0 | 35.6 GB | 262–393 tok/s | Runs great |
| FP16 | 66.9 GB | 217–326 tok/s | Runs great |
Open the full calculator →Everything a NVIDIA H200 (141GB) runsLaguna XS 2.1 (MoE) on other machinesWhat to buy to run it →
Ran Laguna XS 2.1 (MoE) on a NVIDIA H200 (141GB)? Add your real numbers →