cogito:14b

Upstream reference: Cogito v1 Preview Qwen 14B

Publisher: Deep Cogito

Deep Cogito documents an instruction-tuned text model derived from Qwen2.5-14B, with direct-answer and optional thinking modes.

Publisher-described context, separate from Sigma5C observations and recorded catalog statistics.

Published upstream specifications

Base checkpoint

Qwen2.5-14B Source

Published context

128k tokens, publisher notation Source

Upstream license label

Apache-2.0 Source

Publisher-described uses

• Text assistants, coding and STEM text workflows described by the publisher. Source

Reference limitations

• Qwen-derived and Llama-derived Cogito releases have different underlying licenses; the shared family name is not a blanket license. Source

A recorded tag and an upstream card association do not verify the deployed checkpoint, quantization, configured context or current hosted availability.

Publisher sources

• Cogito v1 Preview Qwen 14B official documentation — Deep Cogito. Checked 2026-11-02.

Links

Recorded references do not establish downloadable weights, licensing or current availability.

• Deep Cogito — official site
• Ollama
• Hugging Face
• Official model announcement / documentation

Where cogito:14b comes from

Named in 2 observation pages

• 14B-32B local models — all 47 · V1
• How models scale under concurrent slots · V1