Intel Arc Pro A60 meets the minimum VRAM requirement for Q4 inference of Alibaba-NLP/gte-Qwen2-1.5B-instruct. Review the quantization breakdown below to see how higher precision settings impact VRAM and throughput.
Intel Arc Pro A60 can run Alibaba-NLP/gte-Qwen2-1.5B-instruct with Q4 quantization. At approximately 59 tokens/second, you can expect Good speed - acceptable for interactive use.
You have 9GB headroom, which is sufficient for system overhead and smooth operation.
| Quantization | VRAM needed | VRAM available | Estimated speed | Verdict |
|---|---|---|---|---|
| Q4 | 3GB | 12GB | 58.91 tok/s | ✅ Fits comfortably |
| Q8 | 5GB | 12GB | 46.10 tok/s | ✅ Fits comfortably |
| FP16 | 11GB | 12GB | 24.05 tok/s | ⚠️ Tight fit |