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

COOLmanYT

no firefox support?

hhthrowaway1230

so multiple of these browser wasm demos make me re-download the models, can someone make a cdn for it or some sort u uberfast downloader? just throw some claude credits against it ty!

logicallee

I love this idea. Unfortunately, it says "Unsupported browser/GPU" for me. This is Desktop Chrome version 147 (page says it requires 134+) and I have a 1060 card with 6 GB of RAM on this specific device, so it should fit. I have more than 4 GB of free RAM as well.

agent37

Very cool. Did you happen to try other models like Qwen and was there a difference as opposed to Gemma ?

wesleynepo

Really interesting, I wish I could understand the under the hood better but I guess I don't have all the background needed.

rahimnathwani

How does this part work? "The LLM outputs compact code (~50 tokens) instead of raw Excalidraw JSON (~5,000 tokens)." I see on the left that the LLM is outputting some instructions to add nodes and edges to the diagram. But what is interpreting those commands and turning them into an Excalidraw file?

Sathwickp

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

OsamaJaber

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

locusofself

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.

walthamstow

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

billyp-rva

> "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.

userbinator

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

xnx

It seems like Gemma should replace Gemini Nano as the AI built into Chrome.

busssard

no firefox? sad :(

vismit2000

https://skemio.com