Apple M4 Max 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.
Apple M4 Max can run RedHatAI/Llama-3.2-90B-Vision-Instruct-FP8-dynamic with Q4 quantization. At approximately 14 tokens/second, you can expect Basic speed - best for non-interactive tasks.
You have 84GB headroom, which is sufficient for system overhead and smooth operation.
| Quantization | VRAM needed | VRAM available | Estimated speed | Verdict |
|---|---|---|---|---|
| Q4 | 44GB | 128GB | 14.05 tok/s | ✅ Fits comfortably |
| Q8 | 88GB | 128GB | 9.32 tok/s | ✅ Fits comfortably |
| FP16 | 176GB | 128GB | 5.95 tok/s | ❌ Not recommended |