Can I run this LLM?
Can a NVIDIA H200 (141GB) run Qwen3.8 Flash Next (MoE)?
Qwen · See model card · estimated for a 141.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Qwen3.8 Flash Next (MoE) at Q3_K_M · 92.0 GB · 275–412 tok/s on a NVIDIA H200 (141GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 80.9 GB | 283–425 tok/s | Runs great |
| Q3_K_M | 92.0 GB | 275–412 tok/s | Runs great |
| Q4_K_M | 119.6 GB | 256–385 tok/s | Tight / slow |
| Q5_K_M | 134.7 GB | 247–371 tok/s | Won't fit |
| Q6_K | 168.1 GB | 229–344 tok/s | Won't fit |
| Q8_0 | 188.3 GB | 219–329 tok/s | Won't fit |
| FP16 | 354.0 GB | 163–244 tok/s | Won't fit |
Open the full calculator →Everything a NVIDIA H200 (141GB) runsQwen3.8 Flash Next (MoE) on other machinesWhat to buy to run it →
Ran Qwen3.8 Flash Next (MoE) on a NVIDIA H200 (141GB)? Add your real numbers →