Can I run this LLM?
Can a NVIDIA B200 (192GB) run Hunyuan Hy3 (MoE)?
Hunyuan · Apache 2.0 · estimated for a 192.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Hunyuan Hy3 (MoE) at Q3_K_M · 137.6 GB · 218–327 tok/s on a NVIDIA B200 (192GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 106.7 GB | 237–355 tok/s | Runs great |
| Q3_K_M | 137.6 GB | 218–327 tok/s | Runs great |
| Q4_K_M | 182.2 GB | 195–293 tok/s | Won't fit |
| Q5_K_M | 212.8 GB | 182–273 tok/s | Won't fit |
| Q6_K | 257.3 GB | 166–249 tok/s | Won't fit |
| Q8_0 | 317.7 GB | 148–223 tok/s | Won't fit |
Open the full calculator →Everything a NVIDIA B200 (192GB) runsHunyuan Hy3 (MoE) on other machinesWhat to buy to run it →
Ran Hunyuan Hy3 (MoE) on a NVIDIA B200 (192GB)? Add your real numbers →