Qwen3.5-2B-AWQ-4bit is a 4-bit AWQ quantized version of Alibaba's Qwen 3.5 2B model. It supports multimodal inputs including images and video in addition to text, along with tool calling capabilities. The model is distributed on Hugging Face for efficient local or edge deployment.
In the Multimodal & vision space, Qwen3.5 2B takes a focused approach. It focuses on deploying capable language and vision models on devices with limited memory using AWQ quantization. It is built as an open-source project for developers. The project is open source (Apache-2.0). Qwen3.5 2B is available on the web, the command line, and API.
It is developed by cyankiwi, and it first shipped in 2023. Development happens publicly on GitHub with 30.6k stars and 3.6k commits in the last 90 days. It operates in a well-populated space: PulseGate tracks 14 similar projects. Among its 3 catalogued features are Quantized Inference, Vision Support, and Tool Use.
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