Qwen3.6-35B-A3B-MLX-6bit is a 6-bit quantized version of the Qwen 3.6 model hosted by the lmstudio-community on Hugging Face. It belongs to the class of foundation models and is distributed as a repository containing model weights, tokenizer configuration, and a chat template that supports multimodal inputs.
The repository includes a tokenizer definition with specific pad, end-of-text, and unknown tokens. Its chat template contains logic for processing mixed content, including separate handling for text strings and iterable content. The template detects image and video items, increments internal counters for each, prepends numbered labels such as "Picture 1:" when a flag is set, and inserts special vision markers. It explicitly prevents images or videos from appearing in system messages by raising an exception.
The model is made available through the Hugging Face platform, which provides access to models, datasets, and related resources. No information is given on licensing, pricing, intended user roles, or specific hardware optimizations beyond what is encoded in the repository name and template.
Qwen3.6 35B A3B is a Foundation models & chat product. It focuses on enabling efficient local execution of large multimodal models on Apple silicon with aggressive quantization. Qwen3.6 35B A3B is an open-source project aimed at developers. The project is open source (MIT). It runs on the web, the command line, and API.
lmstudio-community builds and maintains Qwen3.6 35B A3B, 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 3 catalogued features are Quantized Model, MLX Framework, and Vision Capabilities. It exposes integrations via a public API.
Latest indexed changes and source events
lmstudio-community/Qwen3.6-35B-A3B-MLX-6bit verified by the PulseGate indexer
Other apps tracked under the same category.
