NVIDIA L40S meets the minimum VRAM requirement for Q4 inference of google-t5/t5-3b. Review the quantization breakdown below to see how higher precision settings impact VRAM and throughput.
NVIDIA L40S can run google-t5/t5-3b with Q4 quantization. At approximately 199 tokens/second, you can expect Excellent speed - conversational response times under 1 second.
You have 46GB headroom, which is sufficient for system overhead and smooth operation.
| Quantization | VRAM needed | VRAM available | Estimated speed | Verdict |
|---|---|---|---|---|
| Q4 | 2GB | 48GB | 198.85 tok/s | ✅ Fits comfortably |
| Q8 | 3GB | 48GB | 137.68 tok/s | ✅ Fits comfortably |
| FP16 | 6GB | 48GB | 82.96 tok/s | ✅ Fits comfortably |