This is a GPTQ Int4 quantized version of the Qwen3.6-35B-A3B model optimized for reduced memory usage while maintaining performance. It supports vision inputs, complex chat templates, and multimodal content. The model is hosted on Hugging Face for use with Transformers and inference engines.
Qwen3.6 35B A3B is a Quantised & converted weights project. It focuses on deploying a large 35B parameter multimodal model efficiently on consumer or edge hardware using 4-bit quantization. It is built as an open-source project for developers needing efficient LLMs. The project is open source (Open Source). Qwen3.6 35B A3B is available on the web and the command line, and it can be self-hosted.
It is developed by Palmfuture, and it first shipped in 2025. PulseGate's similarity index places it among 10 comparable projects. Key capabilities include Quantized Inference, Vision Support, and Advanced Chat Templates. 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