This is a 4-bit AWQ quantized variant of Alibaba's Qwen3.6 27B model. The quantization enables the large model to run on more accessible hardware while maintaining strong performance. It is distributed on Hugging Face for use with compatible inference engines.
Qwen3.6 27B is a Foundation models & chat project. It focuses on running the powerful 27B Qwen3.6 model efficiently on consumer-grade hardware with reduced memory footprint. It is built as an open-source project for developers. Qwen3.6 27B is open source under the Apache-2.0 license. It ships for the web, the command line, and API.
Alennnndy builds and maintains Qwen3.6 27B, and it first shipped in 2023. The project is developed in the open on GitHub with 31k stars and 3.7k commits in the last 90 days. It competes in a saturated segment with 25 similar apps in PulseGate's index. Among its 3 catalogued features are 4-bit quantization, AWQ, and large context.
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