AMD Instinct MI210 meets the minimum VRAM requirement for Q4 inference of HuggingFaceTB/SmolLM2-135M. Review the quantization breakdown below to see how higher precision settings impact VRAM and throughput.
AMD Instinct MI210 can run HuggingFaceTB/SmolLM2-135M with Q4 quantization. At approximately 253 tokens/second, you can expect Excellent speed - conversational response times under 1 second.
You have 60GB headroom, which is sufficient for system overhead and smooth operation.
| Quantization | VRAM needed | VRAM available | Estimated speed | Verdict |
|---|---|---|---|---|
| Q4 | 4GB | 64GB | 253.06 tok/s | ✅ Fits comfortably |
| Q8 | 7GB | 64GB | 169.30 tok/s | ✅ Fits comfortably |
| FP16 | 15GB | 64GB | 93.55 tok/s | ✅ Fits comfortably |