Show HN: Prompt-to-Excalidraw demo with Gemma 4 E2B in the browser (3.1GB)

I've had excellent luck using Claude Code to generate "mermaid diagrams" for me, and convert them to .png format headlessly using mmdc/puppeteer. Really helped me out with an engineering proposal I just finished. In past years I would have fumbled around with Visio forever and the result would have been worse.

Am I correct in interpreting the title to mean that visiting the page will result in a 3.1GB download?

The Gemma models really are amazing. I was on a flight a few days ago and used E2B to do some basic research on the place I was going to, running the model locally on my Pixel 10 Pro. It gave me basically the same as Gemini or ChatGPT would do when I landed

Small models in the browser are a different optimization problem than small models on a server. On server you chase throughput so you batch. In browser you're stuck at batch size 1, which means kernel launch overhead and memory bandwidth dominate, not FLOPs

Please never do this again. It's insane that the 3.1GB download kicks off as soon as you open the page.

> "OAuth 2.0 authorization code flow with PKCE as a sequence diagram — user, browser, app server, auth server, API"

If you do a Google image search for "OAuth 2.0 PKCE sequence diagram" you get good results also. Maybe if you ask for something more esoteric this becomes valuable? Of course, that also makes hallucinations more likely.

very interesting. Prompt to "generate System Design like ChatGPT end to end". Took about ~3-5 mins the model to download. It generated a reasonably good system design.

just tried it out, must say it's amazing the speed at which it generates these diagrams Is this opensource by any chance? Would love to take a look at the code and understand how it works