§01·model · /models
Qwen3 14B
llmactiveApache-2.0
14B dense LLM by Alibaba (Qwen3) with hybrid thinking / non-thinking modes, Apache-2.0. Twenty cards in this catalogue carry a published recipe for it, and the smallest is a 12 GB board at 4-bit GGUF — that is the practical floor for a 14B, not a comfortable one. Measured here at 123.8 tok/s on an RTX 5090 and 80.6 tok/s on a 16 GB RTX 5080, so the middle of the range keeps interactive speed rather than merely fitting.
Download· 4 variants
§02·same family
5 other models · by nameOther models grouped with Qwen3 14B. Sizes and modalities can differ, and nothing here says whether one fits your GPU — open a model for its own compatibility table.
§03·GPUs that run this model
20 total| GPU | VRAM | Series | Best speed | Min VRAM | Works | Evidence | |
|---|---|---|---|---|---|---|---|
| RTX 5090 | 32GB | 50 | 123.8tokens/s | ✓ | 3benchesrecipe | check ↗ | |
| RTX 5080 | 16GB | 50 | 80.6tokens/s | 16GB | ✓ | 2benchesrecipe | check ↗ |
| RTX 3090 Ti | 24GB | 30 | 76.2tokens/s | 24GB | ✓ | 2benchesrecipe | check ↗ |
| RTX 5070 Ti | 16GB | 50 | 74.3tokens/s | 16GB | ✓ | 2benchesrecipe | check ↗ |
| RTX 3090 | 24GB | 30 | 70tokens/s | 24GB | ✓ | 2benchesrecipe | check ↗ |
| RTX 3080 Ti | 12GB | 30 | 69.9tokens/s | ✓ | 2benchesrecipe | check ↗ | |
| RTX 4080 Super | 16GB | 40 | 64.2tokens/s | 16GB | ✓ | 2benchesrecipe | check ↗ |
| RTX 4080 | 16GB | 40 | 62tokens/s | 16GB | ✓ | 2benchesrecipe | check ↗ |
| RTX 4070 Ti Super | 16GB | 40 | 58.1tokens/s | 16GB | ✓ | 2benchesrecipe | check ↗ |
| RTX 5070 | 12GB | 50 | 54.2tokens/s | 12GB | ✓ | 2benchesrecipe | check ↗ |
| RTX 4070 Ti | 12GB | 40 | 45.8tokens/s | 12GB | ✓ | 2benchesrecipe | check ↗ |
| RTX 4070 Super | 12GB | 40 | 45.5tokens/s | 12GB | ✓ | 2benchesrecipe | check ↗ |
| RTX 5060 Ti | 16GB | 50 | 41.1tokens/s | 16GB | ✓ | 2benchesrecipe | check ↗ |
| RTX 3060 | 12GB | 30 | 35.9tok/s | ✓ | 3benchesrecipe | check ↗ | |
| RTX 4060 Ti 16GB | 16GB | 40 | 27.4tokens/s | 16GB | ✓ | 2benchesrecipe | check ↗ |
| Apple M2 Pro | 16GB | apple | ~ | recipe | check ↗ | ||
| RTX 4070 | 12GB | 40 | ~ | recipe | check ↗ | ||
| RTX 4090 | 24GB | 40 | ~ | recipe | check ↗ | ||
| RX 7800 XT | 16GB | amd | ~ | recipe | check ↗ | ||
| RX 7900 XTX | 24GB | amd | ~ | recipe | check ↗ |
- VRAM
- 32GB
- Best speed
- 123.8tokens/s
- Min VRAM
- Evidence
- 3benchesrecipe
- VRAM
- 16GB
- Best speed
- 80.6tokens/s
- Min VRAM
- 16GB
- Evidence
- 2benchesrecipe
- VRAM
- 24GB
- Best speed
- 76.2tokens/s
- Min VRAM
- 24GB
- Evidence
- 2benchesrecipe
- VRAM
- 16GB
- Best speed
- 74.3tokens/s
- Min VRAM
- 16GB
- Evidence
- 2benchesrecipe
- VRAM
- 24GB
- Best speed
- 70tokens/s
- Min VRAM
- 24GB
- Evidence
- 2benchesrecipe
- VRAM
- 12GB
- Best speed
- 69.9tokens/s
- Min VRAM
- Evidence
- 2benchesrecipe
- VRAM
- 16GB
- Best speed
- 64.2tokens/s
- Min VRAM
- 16GB
- Evidence
- 2benchesrecipe
- VRAM
- 16GB
- Best speed
- 62tokens/s
- Min VRAM
- 16GB
- Evidence
- 2benchesrecipe
- VRAM
- 16GB
- Best speed
- 58.1tokens/s
- Min VRAM
- 16GB
- Evidence
- 2benchesrecipe
- VRAM
- 12GB
- Best speed
- 54.2tokens/s
- Min VRAM
- 12GB
- Evidence
- 2benchesrecipe
- VRAM
- 12GB
- Best speed
- 45.8tokens/s
- Min VRAM
- 12GB
- Evidence
- 2benchesrecipe
- VRAM
- 12GB
- Best speed
- 45.5tokens/s
- Min VRAM
- 12GB
- Evidence
- 2benchesrecipe
- VRAM
- 16GB
- Best speed
- 41.1tokens/s
- Min VRAM
- 16GB
- Evidence
- 2benchesrecipe
- VRAM
- 12GB
- Best speed
- 35.9tok/s
- Min VRAM
- Evidence
- 3benchesrecipe
- VRAM
- 16GB
- Best speed
- 27.4tokens/s
- Min VRAM
- 16GB
- Evidence
- 2benchesrecipe
- VRAM
- 16GB
- Best speed
- Min VRAM
- Evidence
- recipe
- VRAM
- 12GB
- Best speed
- Min VRAM
- Evidence
- recipe
- VRAM
- 24GB
- Best speed
- Min VRAM
- Evidence
- recipe
- VRAM
- 16GB
- Best speed
- Min VRAM
- Evidence
- recipe
- VRAM
- 24GB
- Best speed
- Min VRAM
- Evidence
- recipe
✓ benchmarked·~ runs via recipe (not benchmarked)·— untested·✕doesn't fit