NVIDIA L40S meets the minimum VRAM requirement for Q4 inference of dphn/dolphin-2.9.1-yi-1.5-34b. Review the quantization breakdown below to see how higher precision settings impact VRAM and throughput.
NVIDIA L40S can run dphn/dolphin-2.9.1-yi-1.5-34b with Q4 quantization. At approximately 59 tokens/second, you can expect Good speed - acceptable for interactive use.
You have 31GB headroom, which is sufficient for system overhead and smooth operation.
| Quantization | VRAM needed | VRAM available | Estimated speed | Verdict |
|---|---|---|---|---|
| Q4 | 17GB | 48GB | 59.39 tok/s | ✅ Fits comfortably |
| Q8 | 35GB | 48GB | 44.38 tok/s | ✅ Fits comfortably |
| FP16 | 70GB | 48GB | 20.65 tok/s | ❌ Not recommended |