NVIDIA A100 80GB SXM4 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 A100 80GB SXM4 can run openai/gpt-oss-120b with Q4 quantization. At approximately 61 tokens/second, you can expect Good speed - acceptable for interactive use.
You have 21GB headroom, which is sufficient for system overhead and smooth operation.
| Quantization | VRAM needed | VRAM available | Estimated speed | Verdict |
|---|---|---|---|---|
| Q4 | 59GB | 80GB | 60.95 tok/s | ✅ Fits comfortably |
| Q8 | 117GB | 80GB | 44.22 tok/s | ❌ Not recommended |
| FP16 | 235GB | 80GB | 20.69 tok/s | ❌ Not recommended |