This page is part of the model documentation OpenSource Solutions keeps for the private AI assistants we build and host. We run open source models on our own servers and test them on real business questions before recommending them. All the models we test
AI model
Installed on our servers
ornith-1.5:9b
Ornith AI
Ornith AI's 9-billion-parameter model, the smallest of the Ornith-1.5 family, tuned for terminal-based coding agents and tool calling; reads text, images and video, 262K-token context. The family is built on Qwen3.5 and Gemma 4; the exact base of this size is not published. Licence not stated on the pages checked on 16 October 2026: check it before any client use.
Completion Thinking Tools Vision
Parameters
9.0B
Q4_K_M
Memory
6.6 GB
on the graphics card
Speed
-
tokens per second on our server
Max context
262144
tokens the model can read at once
Licence and cost
- License
- Not stated (checked 16 October 2026)
- Price
- Open weights, licence to confirm. Runs on our servers.
- Family
- qwen35
Which model for your assistant?
A model alone is not an assistant. OpenSource Solutions builds the harness around it: the connection to your documents and tools, the rules it follows, the hosting on your servers or ours, and the measurement on your own questions before you choose. Your data stays on infrastructure you control.