AMD Instinct MI300X meets the minimum VRAM requirement for Q4 inference of trl-internal-testing/tiny-Qwen2ForCausalLM-2.5. Review the quantization breakdown below to see how higher precision settings impact VRAM and throughput.
AMD Instinct MI300X can run trl-internal-testing/tiny-Qwen2ForCausalLM-2.5 with Q4 quantization. At approximately 810 tokens/second, you can expect Excellent speed - conversational response times under 1 second.
You have 188GB headroom, which is sufficient for system overhead and smooth operation.
| Quantization | VRAM needed | VRAM available | Estimated speed | Verdict |
|---|---|---|---|---|
| Q4 | 4GB | 192GB | 810.39 tok/s | ✅ Fits comfortably |
| Q8 | 7GB | 192GB | 545.98 tok/s | ✅ Fits comfortably |
| FP16 | 15GB | 192GB | 271.25 tok/s | ✅ Fits comfortably |