Qwen3.5-2B is a small yet powerful 2 billion parameter multimodal model from the Qwen series, optimized by Unsloth. It supports both text and vision inputs, making it suitable for on-device or resource-constrained applications. The model balances performance and efficiency for various language and vision-language tasks.
Qwen3.5 2B is a Multimodal & vision project. It focuses on running a capable multimodal language model with only 2 billion parameters. Qwen3.5 2B is an open-source project aimed at developers. The project is open source (Open Source). It ships for the web, the command line, and API.
It is developed by Unsloth, and it first shipped in 2025. The category is crowded — PulseGate's index counts 25 comparable projects. Key capabilities include vision support, multimodal input, and efficient size.
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