AMD Instinct MI250X meets the minimum VRAM requirement for Q4 inference of bigcode/starcoder2-3b. Review the quantization breakdown below to see how higher precision settings impact VRAM and throughput.
AMD Instinct MI250X can run bigcode/starcoder2-3b with Q4 quantization. At approximately 571 tokens/second, you can expect Excellent speed - conversational response times under 1 second.
You have 126GB headroom, which is sufficient for system overhead and smooth operation.
| Quantization | VRAM needed | VRAM available | Estimated speed | Verdict |
|---|---|---|---|---|
| Q4 | 2GB | 128GB | 570.73 tok/s | ✅ Fits comfortably |
| Q8 | 3GB | 128GB | 373.85 tok/s | ✅ Fits comfortably |
| FP16 | 6GB | 128GB | 217.86 tok/s | ✅ Fits comfortably |