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
ministral-3:14b
Mistral AI · released 2025-12-02
Mistral AI's 14-billion-parameter model of the Ministral 3 family (December 2025), here the instruct version: text and images, multilingual, with tool use, no reasoning mode. Built for local and edge deployment; fits the 16 GB card of this host.
Completion Tools Vision
Parameters
13.9B
Q4_K_M
Memory
9.1 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
- mistral3
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.