Qwen3.5 35B (Darkbloom)
Use it free in free-pi
~0.7x usage
npx free-pi-cli
/model qwen3.5-35b-darkbloomAbout Qwen3.5 35B (Darkbloom)
Qwen3.5 35B-A3B is a native vision-language model from the Qwen series. It combines linear attention mechanisms with a sparse mixture-of-experts design for higher inference efficiency. In free-pi it is served by Darkbloom. The model details on this page are for the Qwen3.5 35B-A3B model itself.
The model accepts text, image, and video input and produces text. Its context window is about 262,000 tokens and a response can be up to about 82,000 tokens. It supports reasoning, tool calling, and structured outputs. With tool calling, the free-pi agent can read and edit files, run commands, and use free-pi's built-in web search and documentation lookup tools.
It scores 19.3 on the Artificial Analysis Intelligence Index.
In free-pi it is free to use with no API key and no card. It counts as about 0.7x usage, so it uses somewhat more of your daily allowance than the default model.
When to pick it
For a compact open model that reads images and video and runs on Darkbloom instead of the providers behind the other models, pick Qwen3.5 35B (Darkbloom).
For most coding work, pick the default DeepSeek V4 Flash or GLM-5.3 Flash, which have published coding scores and, in the default's case, a longer-lasting allowance.