Ovis2-1B is a compact 1 billion parameter multimodal model that builds on the Qwen architecture. It supports vision inputs and includes advanced tool-calling functionality through structured prompting. The small size makes it suitable for deployment in environments with limited computational resources.
In the Foundation models & chat space, Ovis2 1B takes a focused approach. It focuses on providing lightweight multimodal AI with function calling support for on-device or resource-constrained applications. Ovis2 1B is an open-source project aimed at developers needing compact multimodal models. Ovis2 1B is open source under the Apache-2.0 license. It ships for the web, the command line, and API.
It is developed by ATH-MaaS, and it first shipped in 2024. Development happens publicly on GitHub with 1.5k stars and 1 commit in the last 90 days. Key capabilities include Tool Calling, Multimodal Input, and Small Footprint. It exposes integrations via a public API.
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