AMD Instinct MI300X meets the minimum VRAM requirement for Q4 inference of Qwen/Qwen2.5-72B-Instruct. Review the quantization breakdown below to see how higher precision settings impact VRAM and throughput.
AMD Instinct MI300X can run Qwen/Qwen2.5-72B-Instruct with Q4 quantization. At approximately 141 tokens/second, you can expect Excellent speed - conversational response times under 1 second.
You have 156GB headroom, which is sufficient for system overhead and smooth operation.
| Quantization | VRAM needed | VRAM available | Estimated speed | Verdict |
|---|---|---|---|---|
| Q4 | 36GB | 192GB | 140.73 tok/s | ✅ Fits comfortably |
| Q8 | 71GB | 192GB | 105.04 tok/s | ✅ Fits comfortably |
| FP16 | 142GB | 192GB | 61.67 tok/s | ✅ Fits comfortably |