§01·model · /models
Qwen3 14B
llmactiveApache-2.0
14B LLM by Alibaba (Qwen3) with hybrid thinking / non-thinking modes. Apache-2.0.
Download· 4 variants
§02·GPUs that run this model
20 total| GPU | VRAM | Series | Best speed | Min VRAM | Works | Benchmarks | Recipe | |
|---|---|---|---|---|---|---|---|---|
| RTX 5090 | 32GB | 50 | 123.8tokens/s | ✓ | 3 | recipe | check ↗ | |
| RTX 5080 | 16GB | 50 | 80.6tokens/s | 16GB | ✓ | 2 | recipe | check ↗ |
| RTX 3090 Ti | 24GB | 30 | 76.2tokens/s | 24GB | ✓ | 2 | recipe | check ↗ |
| RTX 5070 Ti | 16GB | 50 | 74.3tokens/s | 16GB | ✓ | 2 | recipe | check ↗ |
| RTX 3090 | 24GB | 30 | 70tokens/s | 24GB | ✓ | 2 | recipe | check ↗ |
| RTX 3080 Ti | 12GB | 30 | 69.9tokens/s | ✓ | 2 | recipe | check ↗ | |
| RTX 4080 Super | 16GB | 40 | 64.2tokens/s | 16GB | ✓ | 2 | recipe | check ↗ |
| RTX 4080 | 16GB | 40 | 62tokens/s | 16GB | ✓ | 2 | recipe | check ↗ |
| RTX 4070 Ti Super | 16GB | 40 | 58.1tokens/s | 16GB | ✓ | 2 | recipe | check ↗ |
| RTX 5070 | 12GB | 50 | 54.2tokens/s | 12GB | ✓ | 2 | recipe | check ↗ |
| RTX 4070 Ti | 12GB | 40 | 45.8tokens/s | 12GB | ✓ | 2 | recipe | check ↗ |
| RTX 4070 Super | 12GB | 40 | 45.5tokens/s | 12GB | ✓ | 2 | recipe | check ↗ |
| RTX 5060 Ti | 16GB | 50 | 41.1tokens/s | 16GB | ✓ | 2 | recipe | check ↗ |
| RTX 3060 | 12GB | 30 | 31.2tokens/s | ✓ | 2 | recipe | check ↗ | |
| RTX 4060 Ti 16GB | 16GB | 40 | 27.4tokens/s | 16GB | ✓ | 2 | recipe | check ↗ |
| Apple M2 Pro | 16GB | apple | ~ | 0 | recipe | check ↗ | ||
| RTX 4070 | 12GB | 40 | ~ | 0 | recipe | check ↗ | ||
| RTX 4090 | 24GB | 40 | ~ | 0 | recipe | check ↗ | ||
| RX 7800 XT | 16GB | amd | ~ | 0 | recipe | check ↗ | ||
| RX 7900 XTX | 24GB | amd | ~ | 0 | recipe | check ↗ |
✓ benchmarked·~ runs via recipe (not benchmarked)·— untested·✕doesn't fit