A w8a8 quantized version of the Qwen2.5-VL-3B-Instruct model published by RedHatAI. It processes both text and visual inputs (images and video) and follows a multimodal chat template. Designed for developers building local multimodal applications with reduced memory requirements.
In the Multimodal & vision space, Qwen2.5 VL 3B Instruct Quantized.w8a8 takes a focused approach. It focuses on enabling efficient on-device or local-server multimodal inference for image and video understanding with a small 3B model. It is built as an open-source project for developers. The project is open source (Open Source). It runs on the web, the command line, and API.
It is developed by RedHatAI, and it first shipped in 2025. The category is crowded — PulseGate's index counts 22 comparable projects. Among its 4 catalogued features are Vision Language, Quantized Weights, and Image Understanding. It exposes integrations via a public API.
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