Can I run this LLM?
Can a NVIDIA B200 (192GB) run Laguna XS 2.1 (MoE)?
Laguna · openmdw-1.1 · estimated for a 192.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Laguna XS 2.1 (MoE) at FP16 · 66.9 GB · 259–389 tok/s on a NVIDIA B200 (192GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 12.2 GB | 331–496 tok/s | Runs great |
| Q3_K_M | 15.6 GB | 325–488 tok/s | Runs great |
| Q4_K_M | 20.6 GB | 317–476 tok/s | Runs great |
| Q5_K_M | 24.0 GB | 312–468 tok/s | Runs great |
| Q6_K | 29.0 GB | 305–457 tok/s | Runs great |
| Q8_0 | 35.6 GB | 296–444 tok/s | Runs great |
| FP16 | 66.9 GB | 259–389 tok/s | Runs great |
Open the full calculator →Everything a NVIDIA B200 (192GB) runsLaguna XS 2.1 (MoE) on other machinesWhat to buy to run it →
Ran Laguna XS 2.1 (MoE) on a NVIDIA B200 (192GB)? Add your real numbers →