Quantization-specific throughput and VRAM requirements for llamafactory/tiny-random-Llama-3 running on NVIDIA L40S.
Speed values come from the compatibility dataset (`estimatedTokensPerSec`) and are sorted by quantization.
For full verdict logic and alternate GPUs, see the canonical compatibility page.
Open full compatibility report| Quantization | VRAM needed | VRAM available | Speed | Verdict |
|---|---|---|---|---|
| Q4 | 4GB | 48GB | 176 tok/s | ✅ Fits |
| Q8 | 7GB | 48GB | 124 tok/s | ✅ Fits |
| FP16 | 15GB | 48GB | 67 tok/s | ✅ Fits |