Holo-3.1-35B-A3B is an open-source multimodal model supporting text, image, and video inputs. It features advanced chat templates, tool calling, and can be deployed locally via Docker or pip. The model is designed for developers building AI applications that require vision and language understanding.
In the Foundation models & chat space, Holo 3.1 35B A3B takes a focused approach. It focuses on running large multimodal AI models locally with persistent context and tool integration. It is built as an open-source project for developers. The project is open source (Open Source). It ships for the web, the command line, and API, and it can be self-hosted.
Behind Holo 3.1 35B A3B is Hcompany, and it first shipped in 2025. Among its 4 catalogued features are Multimodal Processing, Vision Understanding, and Tool Use.
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