Qwen2.5-14B-Instruct
Alibaba CloudQwen2.5-14B-Instruct (14.7B dense, 48 layers, GQA, 128K context, 29+ languages), instruction-tuned general chat SKU; Qwen2.5 release Sep 2024. Verified live on HF June 2026.
Qwen2.5-14B-Instruct (14.7B dense, 48 layers, GQA, 128K context, 29+ languages), instruction-tuned general chat SKU; Qwen2.5 release Sep 2024. Verified live on HF June 2026.
Openness
3 high confidence- weights
- open(Apache-2.0, on HF)
- data
- closed
- code
- partial(inference/chat template
- license
- Apache-2.0(OSI permissive)
OSI Apache-2.0 open weights; post-training data and training code closed -> open_weights.
- https://huggingface.co/Qwen/Qwen2.5-14B-Instruct recorded 2026-06-04
Apache-2.0 license, 14.7B instruct model card, downloadable BF16 weights
Adoption
4 high confidence~2.22M downloads last month for the 14B-Instruct SKU on HF; one of the most-pulled mid-size instruct models in the dominant Qwen2.5 family. Solidly in the 1-10M band on measured monthly downloads.
- https://huggingface.co/Qwen/Qwen2.5-14B-Instruct recorded 2026-06-04
~2,216,468 downloads last month
Capability
3 medium confidenceCapable mid-size (14B) 2024 general chat model; strong-for-size but well below 2026 frontier and below larger Qwen2.5/3 SKUs. HF card does not inline MMLU/MMLU-Pro numbers; scored 3 on size/class with medium confidence.
- https://huggingface.co/Qwen/Qwen2.5-14B-Instruct recorded 2026-06-04
14B instruct general-chat model card, vendor capability claims; defers benchmarks to Qwen2.5 blog
Unchanged since 2026-07-29 (last edited, not re-checked)