NVIDIA H200 SXM 141GB meets the minimum VRAM requirement for Q4 inference of RedHatAI/Llama-3.2-90B-Vision-Instruct-FP8-dynamic. Review the quantization breakdown below to see how higher precision settings impact VRAM and throughput.
NVIDIA H200 SXM 141GB can run RedHatAI/Llama-3.2-90B-Vision-Instruct-FP8-dynamic with Q4 quantization. At approximately 138 tokens/second, you can expect Excellent speed - conversational response times under 1 second.
You have 97GB headroom, which is sufficient for system overhead and smooth operation.
| Quantization | VRAM needed | VRAM available | Estimated speed | Verdict |
|---|---|---|---|---|
| Q4 | 44GB | 141GB | 137.52 tok/s | ✅ Fits comfortably |
| Q8 | 88GB | 141GB | 89.66 tok/s | ✅ Fits comfortably |
| FP16 | 176GB | 141GB | 56.86 tok/s | ❌ Not recommended |