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
hf.co/unsloth/Qwen3.8-27B-GGUF:UD-Q3_K_XL
Alibaba (Qwen), quantization by Unsloth · released 2026-08-14
Successor of Qwen3.6-27B with the same architecture and new post-training, aimed at agent work. Reasons more by default, which makes it slower. Here in Unsloth's 3-bit dynamic quantization (UD-Q3_K_XL).
Completion Thinking Tools Vision
Parameters
27.3B
Q3_K_L
Memory
14.1 GB
on the graphics card
Speed
29
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
- 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.