§01·model · /models
Llama 3.1 8B
llmactive
§02·GPUs that run this model
7 total| GPU | VRAM | Series | Best speed | Min VRAM | Works | Benchmarks | |
|---|---|---|---|---|---|---|---|
| RTX 4090 | 24GB | 40 | 96.12tokens/s | ✓ | 1 | check ↗ | |
| RTX 3060 Ti | 8GB | 30 | 57.34tokens/s | 8GB | ✓ | 1 | check ↗ |
| RTX 5060 Ti | 16GB | 50 | 55.5tokens/s | 16GB | ✓ | 2 | check ↗ |
| RTX 4070 | 12GB | 40 | 52.1tokens/s | ✓ | 1 | check ↗ | |
| RX 7900 XTX | 24GB | amd | 51.3tokens/s | 24GB | ✓ | 1 | check ↗ |
| RTX 3060 | 12GB | 30 | 42tokens/s | ✓ | 1 | check ↗ | |
| RTX 4060 Ti 16GB | 16GB | 40 | 34tokens/s | 16GB | ✓ | 1 | check ↗ |