Qwen3.5-122B-A10B-GGUF is a quantized release of the Qwen3.5-122B-A10B foundation model hosted on Hugging Face by Unsloth. It is provided in GGUF format for local inference.
The model supports processing of text, image, and video inputs through a chat template that handles multimodal content. Its template includes specific tokens such as vision_start, vision_end, image_pad, and video_pad, along with logic for counting vision elements and raising exceptions for unsupported cases like videos in system messages. The template also accommodates tool calling by formatting available functions when tools are supplied in the messages.
It is delivered as a repository on the Hugging Face platform containing GGUF quantized files. The page includes a chat template implementation in a macro-based format that processes message lists, handles different content types, and generates appropriate system prompts for tool use.
The model belongs to the class of foundation models. No pricing, licensing details, or target audience beyond the repository context are stated.
Qwen3.5 122B A10B sits in PulseGate's Foundation models & chat category. It focuses on running large multimodal language models efficiently on consumer or edge hardware with reduced memory requirements. It is built as an open-source project for developers and researchers. Qwen3.5 122B A10B is open source under the Apache-2.0 license. The product ships for the web, the command line, and API.
Behind Qwen3.5 122B A10B is Unsloth, and the product first shipped in 2023. Development happens publicly on GitHub with 68.7k stars and 1.2k commits in the last 90 days. The category is crowded — PulseGate's index counts 25 comparable apps. Key capabilities include Quantized Weights, GGUF Format, and Vision Support.
Latest indexed changes and source events
unsloth/Qwen3.5-122B-A10B-GGUF verified by the PulseGate indexer
Other apps tracked under the same category.
