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
gemma4:12b-it-q8_0
Google · released 2026-06-03
Google's Gemma 4 12B in 8-bit quantization (Q8_0): the same model as gemma4:12b with less rounding, so closer to the original, at 12.8 GB instead of 7.6 GB. Shows on the bench whether the extra memory buys better answers.
Completion Thinking Tools Vision
Parameters
11.9B
Q8_0
Memory
12.8 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
- Apache 2.0
- Price
- Free, open weights. Runs on our servers: no per-token cost.
- Family
- gemma4
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.