Qwopus3.6-27B-v2-MTP-GGUF is a GGUF-quantized multimodal model supporting image and text inputs with advanced multi-token prediction (MTP) capabilities for faster inference. It combines reasoning, coding, and vision abilities in a single model. It is compatible with llama.cpp-based tools and local inference runtimes.
In the Foundation models & chat space, Qwopus3.6 27B V2 MTP takes a focused approach. It focuses on running a large multimodal reasoning model locally with enhanced inference speed via speculative decoding. Qwopus3.6 27B V2 MTP is an open-source project aimed at developers. The project is open source (Apache-2.0). The product ships for the web, the command line, and API.
Jackrong builds and maintains Qwopus3.6 27B V2 MTP, and the product first shipped in 2026. The project is developed in the open on GitHub with 1.6k stars and 18 commits in the last 90 days. Among its 3 catalogued features are Vision Understanding, Multi-Token Prediction, and Speculative Decoding.
Latest indexed changes and source events
Jackrong/Qwopus3.6-27B-v2-MTP-GGUF verified by the PulseGate indexer
Other apps tracked under the same category.
