Alibaba/Qwen · open-weights model
Qwen3-14B
Qwen3-14B is a 14.8B-parameter model by Alibaba/Qwen. Its smallest quant (Q4_K_M) needs at least 10.9GB of GPU-addressable memory at 8K context; it loads cleanly at a quality quant on 36 of the 50 machines we track.
- Parameters
- 14.8B
- Layers
- 40
- Max context
- 40K
- Attention
- GQA
- License
- apache-2.0
Config from Qwen/Qwen3-14B
Quants and what they need
Measured file sizes; “needs” = weights + KV cache at 8K context + overhead.
| Quant | File size | Needs ≥ |
|---|---|---|
| Q8_0 | 15.7 GB | 17.6 GB |
| Q6_K | 12.1 GB | 14.0 GB |
| Q5_K_M | 10.5 GB | 12.4 GB |
| Q4_K_M | 9.0 GB | 10.9 GB |
What runs Qwen3-14B
Every machine we track, graded at its best clean-fit quant.
Verdicts computed from published specs and measured GGUF sizes — how the math works.