neo-unify
Toy-scale unified multimodal model experiments — encoder-free understanding & generation with Mixture-of-Transformers on MLX/Apple Silicon
Experiment with a simple model that understands and generates images without using traditional encoding methods.
Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.
Get an email alert on its next release or when it starts trending — never miss the moment.
Free · no card · unsubscribe anytimeToy-scale unified multimodal model experiments — encoder-free understanding & generation with Mixture-of-Transformers on MLX/Apple Silicon
neo-unify has 51 stars on GitHub. It has been forked 1 times. neo-unify is written mainly in Python. It has been in active development since 2026. Its main topics are apple-silicon, deep-learning, flow-matching, generative-ai.
What is neo-unify?
Toy-scale unified multimodal model experiments — encoder-free understanding & generation with Mixture-of-Transformers on MLX/Apple Silicon
Is neo-unify open source?
neo-unify is an open-source project.
Is neo-unify free?
Yes. neo-unify is free and open source — you can use, modify and self-host it.
What language is neo-unify written in?
neo-unify is written mainly in Python.
Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.
[](https://olud.ai/project/eren23-neo-unify.html)
Measured from GitHub topics shared by both projects, weighted by how rare each topic is.