NVIDIA H100 SXM5 80GB 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 H100 SXM5 80GB can run RedHatAI/Llama-3.2-90B-Vision-Instruct-FP8-dynamic with Q4 quantization. At approximately 91 tokens/second, you can expect Good speed - acceptable for interactive use.
You have 36GB headroom, which is sufficient for system overhead and smooth operation.
| Quantization | VRAM needed | VRAM available | Estimated speed | Verdict |
|---|---|---|---|---|
| Q4 | 44GB | 80GB | 90.82 tok/s | ✅ Fits comfortably |
| Q8 | 88GB | 80GB | 70.34 tok/s | ❌ Not recommended |
| FP16 | 176GB | 80GB | 35.21 tok/s | ❌ Not recommended |