NVIDIA H200 SXM 141GB meets the minimum VRAM requirement for Q4 inference of openai/gpt-oss-120b. Review the quantization breakdown below to see how higher precision settings impact VRAM and throughput.
NVIDIA H200 SXM 141GB can run openai/gpt-oss-120b with Q4 quantization. At approximately 125 tokens/second, you can expect Excellent speed - conversational response times under 1 second.
You have 82GB headroom, which is sufficient for system overhead and smooth operation.
| Quantization | VRAM needed | VRAM available | Estimated speed | Verdict |
|---|---|---|---|---|
| Q4 | 59GB | 141GB | 124.97 tok/s | ✅ Fits comfortably |
| Q8 | 117GB | 141GB | 103.75 tok/s | ✅ Fits comfortably |
| FP16 | 235GB | 141GB | 47.29 tok/s | ❌ Not recommended |