This is a GGUF-formatted, quantized release of the Qwen3.5-122B model (with A10B active parameters, Mixture-of-Experts, and MTP). It supports multimodal inputs and is optimized for local inference using tools that consume the GGUF format. The model is distributed via the Unsloth organization on Hugging Face.
In the Foundation models & chat space, Qwen3.5 122B A10B MTP takes a focused approach. It focuses on running a large-scale Qwen 3.5 model locally using GGUF-compatible tools like llama.cpp. It is built as an open-source project for developers and local AI enthusiasts. Qwen3.5 122B A10B MTP is open source under the Apache-2.0 license. It ships for the web, the command line, and API.
Behind Qwen3.5 122B A10B MTP is Unsloth, and it first shipped in 2023. The project is developed in the open on GitHub with 68.7k stars and 1.2k commits in the last 90 days. It operates in a well-populated space: PulseGate tracks 10 similar projects. Key capabilities include GGUF Format, mixture of Experts, and multimodal.
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