NVIDIA H200 SXM 141GB meets the minimum VRAM requirement for Q4 inference of Qwen/Qwen2.5-72B-Instruct. Review the quantization breakdown below to see how higher precision settings impact VRAM and throughput.
NVIDIA H200 SXM 141GB can run Qwen/Qwen2.5-72B-Instruct with Q4 quantization. At approximately 135 tokens/second, you can expect Excellent speed - conversational response times under 1 second.
You have 105GB headroom, which is sufficient for system overhead and smooth operation.
| Quantization | VRAM needed | VRAM available | Estimated speed | Verdict |
|---|---|---|---|---|
| Q4 | 36GB | 141GB | 134.69 tok/s | ✅ Fits comfortably |
| Q8 | 71GB | 141GB | 101.87 tok/s | ✅ Fits comfortably |
| FP16 | 142GB | 141GB | 52.07 tok/s | ❌ Not recommended |