Quantization-specific throughput and VRAM requirements for Qwen/Qwen2.5-72B-Instruct running on NVIDIA H200 SXM 141GB.
Speed values come from the compatibility dataset (`estimatedTokensPerSec`) and are sorted by quantization.
For full verdict logic and alternate GPUs, see the canonical compatibility page.
Open full compatibility report| Quantization | VRAM needed | VRAM available | Speed | Verdict |
|---|---|---|---|---|
| Q4 | 36GB | 141GB | 135 tok/s | ✅ Fits |
| Q8 | 71GB | 141GB | 102 tok/s | ✅ Fits |
| FP16 | 142GB | 141GB | 52 tok/s | ❌ Not recommended |