Intel Arc Pro A40 meets the minimum VRAM requirement for Q4 inference of petals-team/StableBeluga2. Review the quantization breakdown below to see how higher precision settings impact VRAM and throughput.
Intel Arc Pro A40 can run petals-team/StableBeluga2 with Q4 quantization. At approximately 43 tokens/second, you can expect Moderate speed - useful for batch processing.
VRAM usage will be very close to your GPU's limit. Consider closing other applications or using Q3 quantization for more margin.
| Quantization | VRAM needed | VRAM available | Estimated speed | Verdict |
|---|---|---|---|---|
| Q4 | 4GB | 6GB | 43.34 tok/s | ✅ Fits comfortably |
| Q8 | 7GB | 6GB | 30.11 tok/s | ❌ Not recommended |
| FP16 | 15GB | 6GB | 16.64 tok/s | ❌ Not recommended |