Hobby project, I wanted to "ship a useful model in a web browser". so I distilled a small sentence encoder from MiniLM with ternary quantization-aware training. Also wrote the inference engine from scratch and shipped in Rust → WASM SIMD.
It's an embeddings model, not an LLM: text goes in, a 384-dim vector comes out, and cosine similarity between two vectors tells you how related the texts are — regardless of shared words ("reset my password" ↔ "I forgot my password" → 0.88). Used for semantic search, FAQ/intent matching, and clustering. Running it on-device means search-as-you-type semantic search is performant with no API dependencies.
gte-small outscores all-MiniLM-L6 on MTEB (~61 vs ~56 avg per the GTE paper). MiniLM is ternlight's teacher (ternlight holds 0.84 Spearman fidelity to teacher).
I haven't run a head-to-head yet; STS-B/MTEB numbers are on the roadmap. Also on the roadmap is to distill gte-small as teacher.
but also maybe you could put a button on the landing page to trigger the demo because it's a bit startling to hear my fans go crazy when opening a webpage.
That's... how the web works? You download things on demand.
There are JS files larger than 7MB in the wild. They run on JIT engines that displayed severe CVEs over the years. PDFs, video running directly on special hardware encoders. That's the web now.
Very cool! I'd love to point it at my own corpus to index/embed. Would be cool if you could give it a link to a markdown file or even a website to crawl.
Hobby project, I wanted to "ship a useful model in a web browser". so I distilled a small sentence encoder from MiniLM with ternary quantization-aware training. Also wrote the inference engine from scratch and shipped in Rust → WASM SIMD.
It's an embeddings model, not an LLM: text goes in, a 384-dim vector comes out, and cosine similarity between two vectors tells you how related the texts are — regardless of shared words ("reset my password" ↔ "I forgot my password" → 0.88). Used for semantic search, FAQ/intent matching, and clustering. Running it on-device means search-as-you-type semantic search is performant with no API dependencies.
Demo (2k React docs, fully on-device): https://ternlight-demo.vercel.app
Two tiers on npm: - @ternlight/base (7 MB, ~5 ms/embed, more capable embedings) - @ternlight/mini (5 MB wire, ~2.5 ms/embed).
Bundled for Node and browsers.
Repo - see technical details (MIT, training pipeline included): https://github.com/soycaporal/ternlight
Curious if this is something useful, what are the use cases for on-device embeddings.
Awesome! Besides size, how does this compare to gte-small?
gte-small outscores all-MiniLM-L6 on MTEB (~61 vs ~56 avg per the GTE paper). MiniLM is ternlight's teacher (ternlight holds 0.84 Spearman fidelity to teacher). I haven't run a head-to-head yet; STS-B/MTEB numbers are on the roadmap. Also on the roadmap is to distill gte-small as teacher.
This is cool!
but also maybe you could put a button on the landing page to trigger the demo because it's a bit startling to hear my fans go crazy when opening a webpage.
Agree. But this also reminds me fondly of the days where the sounds of my computer so intimately indicated what’s going on.
Amiga floppy disk sounds are the deepest of sense memories.
I added an offline search engine to app.wazzup.im/search (no login or payment required).
First search downloads the model from the internet and subsequent runs are from the cache.
The model is very small so it's not the best for everything but it's good for basic math and coding.
Give it a try.
Can the 30 second embedding time be done beforehand and sent to the browser?
Inference is nice and quick after that.
yes, you could run a 1 time indexing run on the server side, and just ship the embeddings to frontend
Great, now my websites are gonna push entire LLMs onto my browser in order to use my CPU to make inferences about my shopping habits or whatever.
Disabling WASM is the new disable JavaScript
Ha, I was literally thinking this but from the other side.
"Hmm, 7MB would barely make a dent in the size of the app and allow us to do some of our basic ML without calling the backend"
Probably a lot more practical to use this though: https://developer.apple.com/apple-intelligence/
Why do these things download into the browser automatically? This could be used to distribute malware and also or hog excessive browser memory.
That's... how the web works? You download things on demand.
There are JS files larger than 7MB in the wild. They run on JIT engines that displayed severe CVEs over the years. PDFs, video running directly on special hardware encoders. That's the web now.
A WASM model is not that offensive.
Very cool! I'd love to point it at my own corpus to index/embed. Would be cool if you could give it a link to a markdown file or even a website to crawl.
What we need is a W3C LLM API.
If it was like Math (Math.round, Math.PI, etc.) it could be Language, as in:
and maybe even static methods on ImageI think standardizing the runtime is pretty effective, it then open up portability