AMD Instinct MI250X meets the minimum VRAM requirement for Q4 inference of sshleifer/tiny-gpt2. Review the quantization breakdown below to see how higher precision settings impact VRAM and throughput.
AMD Instinct MI250X can run sshleifer/tiny-gpt2 with Q4 quantization. At approximately 463 tokens/second, you can expect Excellent speed - conversational response times under 1 second.
You have 124GB headroom, which is sufficient for system overhead and smooth operation.
| Quantization | VRAM needed | VRAM available | Estimated speed | Verdict |
|---|---|---|---|---|
| Q4 | 4GB | 128GB | 463.36 tok/s | ✅ Fits comfortably |
| Q8 | 7GB | 128GB | 309.54 tok/s | ✅ Fits comfortably |
| FP16 | 15GB | 128GB | 170.20 tok/s | ✅ Fits comfortably |