Can I run this LLM?
Can a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB) run Laguna S 2.1 (MoE)?
Laguna · openmdw-1.1 · estimated for a 144.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Laguna S 2.1 (MoE) at FP16 · 235.1 GB · 32–48 tok/s on a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q3_K_M | 50.7 GB | 256–385 tok/s | Runs great |
| Q4_K_M | 71.3 GB | 233–350 tok/s | Runs great |
| Q5_K_M | 83.8 GB | 221–332 tok/s | Runs great |
| Q6_K | 97.0 GB | 210–314 tok/s | Runs great |
| Q8_0 | 124.9 GB | 189–283 tok/s | Runs great |
| FP16 | 235.1 GB | 32–48 tok/s | Runs great |
Open the full calculator →Everything a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB) runsLaguna S 2.1 (MoE) on other machinesWhat to buy to run it →
Ran Laguna S 2.1 (MoE) on a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB)? Add your real numbers →