Hacker News Reader

This is a Google's Gemini flash 2.5 model with native image output capability. It's fast, relatively cheap and SOTA-quality, and available via API. I think getting this kind of quality in open source models will need some time, probably first from Chinese models and then from BlackForestLabs or Google's open source (Gemma) team.

Outside of Google Deepmind open sourcing the code and weights of AlphaFold, I don't think they've released any of their GenAI stuff (Imagen, Gemini, Flash 2.5, etc).

The best multimodal models that you can run locally right now are probably Qwen-Edit 20b, and Kontext.Dev.

https://qwenlm.github.io/blog/qwen-image-edit

https://bfl.ai/blog/flux-1-kontext-dev

Google also open sources Gemma LLMs and embedding models, which are quite good at the time of release (SOTA or near-SOTA in the open source field).

Oh very nice I wasn't aware of that [1] [2]. Adding the links as well.

[1] https://deepmind.google/models/gemma

[2] https://huggingface.co/google/gemma-7b [2]

Flux Kontext has similar quality, is open weight, and the outputs can be used commercially, however prompt adherence is good-but-not-as-good.