All of our models run locally, on our own small server — free and unrestricted. Everything below shares the same GPU, so only one model stays loaded at a time; switching takes a few seconds to a minute while the previous one unloads.
General multilingual chat (German/EU-focused)
General conversation, brainstorming, explanations, and multilingual chat — trained across all 24 official EU languages.
Teuken is a locally-hosted language model that can assist with a variety of tasks including:
We are using the model Teuken-7B, developed in Germany by Fraunhofer, Forschungszentrum Jülich, TU Dresden, and DFKI.
Funded by the German Federal Ministry of Economics and Climate Protection (BMWK) in the context of the OpenGPT-X project.
The model runs entirely on our local servers in Germany.
Coding-focused — best for code, debugging, dev tasks
Writing and reviewing code, debugging, explaining errors, and as a coding interface for other tools (e.g. captradeai.com).
Qwen2.5-Coder is a coding-focused language model, well suited for:
We are using Qwen2.5-Coder-14B-Instruct, developed by Alibaba's Qwen team, quantized to run on our small server.
The model runs entirely on our local servers.
Text-to-image — fast, high quality, 4-step generation
Generating original images from a text prompt — art, concepts, illustrations, anything you can describe.
FLUX.1-schnell is an open, permissively-licensed image generation model. It's a "distilled" model, meaning it produces a finished image in as few as 4 steps — most models need 20-50 — so generation stays fast even on our own modest GPU.
We are using FLUX.1-schnell, developed by Black Forest Labs, Apache 2.0 licensed.
The model runs entirely on our local servers.
Image-to-video — animate one of your generated images
Turning a still image into a few seconds of video — pick one of your own generated images, or paste an image URL.
LTX-Video takes a source image plus a text prompt and generates a short video from it. It's the lightest of the current open image-to-video models — chosen specifically so it fits alongside our other models on one shared GPU.
We are using LTX-Video, developed by Lightricks.
The model runs entirely on our local servers.
More models will be added here as they become available.