A GGUF quantized variant of a 27-billion parameter model specialized for coding tasks (Qwopus3.6) that also includes multimodal (vision) capabilities. It uses NVFP4 quantization for efficient local inference. The model supports advanced prompting formats and is suitable for code generation and vision-language tasks on compatible hardware.
In the Coding AI & assistants space, Qwopus3.6 27B Coder MTP takes a focused approach. It focuses on running large coding and multimodal models locally with low memory footprint via quantization. Qwopus3.6 27B Coder MTP is an open-source project aimed at developers and AI researchers. Qwopus3.6 27B Coder MTP is open source under the MIT license. It runs on the web, the command line, and API.
It is developed by michaelw9999, and it first shipped in 2026. Development happens publicly on GitHub with 38 stars and 84 commits in the last 90 days. It operates in a well-populated space: PulseGate tracks 9 similar projects. Among its 4 catalogued features are GGUF Format, Vision Support, and Code Generation.
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