Can I run this LLM?
Can a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB) run Hunyuan Hy3 (MoE)?
Hunyuan · Apache 2.0 · estimated for a 144.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Hunyuan Hy3 (MoE) at Q8_0 · 317.5 GB · 19–28 tok/s on a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 97.1 GB | 201–301 tok/s | Runs great |
| Q3_K_M | 128.9 GB | 169–253 tok/s | Runs great |
| Q4_K_M | 181.1 GB | 53–79 tok/s | Runs great |
| Q5_K_M | 212.9 GB | 37–56 tok/s | Runs great |
| Q6_K | 246.5 GB | 28–43 tok/s | Runs great |
| Q8_0 | 317.5 GB | 19–28 tok/s | Runs great |
Open the full calculator →Everything a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB) runsHunyuan Hy3 (MoE) on other machinesWhat to buy to run it →
Ran Hunyuan Hy3 (MoE) on a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB)? Add your real numbers →