NVIDIA H200 SXM 141GB meets the minimum VRAM requirement for Q4 inference of MiniMaxAI/MiniMax-M2.1. Review the quantization breakdown below to see how higher precision settings impact VRAM and throughput.
NVIDIA H200 SXM 141GB can run MiniMaxAI/MiniMax-M2.1 with Q4 quantization. At approximately 79 tokens/second, you can expect Good speed - acceptable for interactive use.
You have 13GB headroom, which is sufficient for system overhead and smooth operation.
| Quantization | VRAM needed | VRAM available | Estimated speed | Verdict |
|---|---|---|---|---|
| Q4 | 128GB | 141GB | 78.93 tok/s | ✅ Fits comfortably |
| Q8 | 256GB | 141GB | 54.99 tok/s | ❌ Not recommended |
| FP16 | 512GB | 141GB | 28.89 tok/s | ❌ Not recommended |