This is a 4B parameter quantized version of the Qwen3-VL vision-language model optimized for MLX. It supports multimodal inputs combining text and images and can be used for visual question answering, document understanding, and tool-calling tasks. The model is distributed on Hugging Face for local inference via libraries such as Transformers or MLX.
Qwen3 VL 4B Instruct is a Foundation models & chat product. It focuses on running advanced multimodal AI models locally with reduced memory requirements. Qwen3 VL 4B Instruct is an open-source project aimed at developers. The project is open source (MIT). Qwen3 VL 4B Instruct is available on the web, the command line, and API.
It is developed by lmstudio-community, and the product first shipped in 2024. The project is developed in the open on GitHub with 5.2k stars and 419 commits in the last 90 days. It competes in a saturated segment with 25 similar apps in PulseGate's index. Among its 4 catalogued features are Vision-Language Model, Quantized Weights, and MLX Format.
Latest indexed changes and source events
lmstudio-community/Qwen3-VL-4B-Instruct-MLX-5bit verified by the PulseGate indexer
Other apps tracked under the same category.
