NVIDIA H100 SXM5 80GB meets the minimum VRAM requirement for Q4 inference of AI-MO/Kimina-Prover-72B. Review the quantization breakdown below to see how higher precision settings impact VRAM and throughput.
NVIDIA H100 SXM5 80GB can run AI-MO/Kimina-Prover-72B with Q4 quantization. At approximately 104 tokens/second, you can expect Excellent speed - conversational response times under 1 second.
You have 45GB headroom, which is sufficient for system overhead and smooth operation.
| Quantization | VRAM needed | VRAM available | Estimated speed | Verdict |
|---|---|---|---|---|
| Q4 | 35GB | 80GB | 104.18 tok/s | ✅ Fits comfortably |
| Q8 | 70GB | 80GB | 75.33 tok/s | ✅ Fits comfortably |
| FP16 | 141GB | 80GB | 39.80 tok/s | ❌ Not recommended |