AI Potluck
Model components / Fine-tuned / chat models

Qwen2.5-14B-Instruct

Alibaba Cloud

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.

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
3.0
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.

Adoption

4 high confidence
4.0

~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.

Capability

3 medium confidence
3.0

Capable 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.

Unchanged since 2026-07-29 (last edited, not re-checked)