ThinkingCap-Qwen3.6-27B is an open-source large language model designed for efficient local inference, offering Qwen3.6 capabilities with 50% fewer thinking tokens. It is suitable for researchers and developers seeking customizable, high-performance LLMs for text-based tasks.
ThinkingCap Qwen3.6 27B is a Foundation models & chat project. It focuses on providing an efficient, open-source large language model for local inference and development. It is built as an open-source project for machine learning researchers. The project is open source (MIT). It runs on the command line, and it can be self-hosted.
Behind ThinkingCap Qwen3.6 27B is bottlecapai, and it first shipped in 2022. Development happens publicly on GitHub with 14.9k stars and 466 commits in the last 90 days. Among its 5 catalogued features are open weights, reduced token usage, and local inference.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do