This repository contains a w8a8 quantized version of the Qwen3.5-9B model from RedHatAI. It supports both text and vision inputs and is optimized for lower memory usage and faster inference. The model includes vision tower components and is compatible with the Transformers library.
Qwen3.5 9B Quantized.w8a8 is a Multimodal & vision project. It focuses on running large language and vision models with reduced memory footprint using 8-bit quantization. It is built as an open-source project for developers building AI applications. Qwen3.5 9B Quantized.w8a8 is open source under the Apache-2.0 license. It ships for the web, the command line, and API.
RedHatAI builds and maintains Qwen3.5 9B Quantized.w8a8, and it first shipped in 2019. The project is developed in the open on GitHub with 3.6k stars and 165 commits in the last 90 days. It competes in a saturated segment with 25 similar projects in PulseGate's index. Key capabilities include Quantized Weights, Vision Support, and Chat Template. 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