NVIDIA H100 PCIe 80GB meets the minimum VRAM requirement for Q4 inference of deepseek-ai/DeepSeek-OCR. Review the quantization breakdown below to see how higher precision settings impact VRAM and throughput.
NVIDIA H100 PCIe 80GB can run deepseek-ai/DeepSeek-OCR with Q4 quantization. At approximately 414 tokens/second, you can expect Excellent speed - conversational response times under 1 second.
You have 78GB headroom, which is sufficient for system overhead and smooth operation.
| Quantization | VRAM needed | VRAM available | Estimated speed | Verdict |
|---|---|---|---|---|
| Q4 | 2GB | 80GB | 413.89 tok/s | ✅ Fits comfortably |
| Q8 | 4GB | 80GB | 291.47 tok/s | ✅ Fits comfortably |
| FP16 | 7GB | 80GB | 151.95 tok/s | ✅ Fits comfortably |