RTX 4070 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 4070 can run petals-team/StableBeluga2 with Q4 quantization. At approximately 89 tokens/second, you can expect Good speed - acceptable for interactive use.
You have 8GB headroom, which is sufficient for system overhead and smooth operation.
| Quantization | VRAM needed | VRAM available | Estimated speed | Verdict |
|---|---|---|---|---|
| Q4 | 4GB | 12GB | 88.99 tok/s | ✅ Fits comfortably |
| Q8 | 7GB | 12GB | 59.82 tok/s | ✅ Fits comfortably |
| FP16 | 15GB | 12GB | 34.30 tok/s | ❌ Not recommended |