RTX 4060 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.
RTX 4060 can run petals-team/StableBeluga2 with Q4 quantization. At approximately 45 tokens/second, you can expect Moderate speed - useful for batch processing.
You have 4GB headroom, which is sufficient for system overhead and smooth operation.
| Quantization | VRAM needed | VRAM available | Estimated speed | Verdict |
|---|---|---|---|---|
| Q4 | 4GB | 8GB | 45.25 tok/s | ✅ Fits comfortably |
| Q8 | 7GB | 8GB | 32.02 tok/s | ⚠️ Tight fit |
| FP16 | 15GB | 8GB | 16.70 tok/s | ❌ Not recommended |