RX 7900 XT 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.
RX 7900 XT can run Alibaba-NLP/gte-Qwen2-1.5B-instruct with Q4 quantization. At approximately 117 tokens/second, you can expect Excellent speed - conversational response times under 1 second.
You have 17GB headroom, which is sufficient for system overhead and smooth operation.
| Quantization | VRAM needed | VRAM available | Estimated speed | Verdict |
|---|---|---|---|---|
| Q4 | 3GB | 20GB | 117.12 tok/s | ✅ Fits comfortably |
| Q8 | 5GB | 20GB | 86.17 tok/s | ✅ Fits comfortably |
| FP16 | 11GB | 20GB | 48.77 tok/s | ✅ Fits comfortably |