cd /news/machine-learning/ternlight-7-mb-embedding-model-that-… · home topics machine-learning article
[ARTICLE · art-48642] src=ternlight-demo.vercel.app ↗ pub= topic=machine-learning verified=true sentiment=↑ positive

Ternlight – 7 MB embedding model that runs in browser (WASM)

Ternlight released a 7 MB embedding model that runs entirely in the browser via WebAssembly, eliminating the need for API calls or servers. The model, available as an npm package, generates embeddings in about 5 milliseconds on CPU, enabling local semantic search and similarity matching without network requests.

read1 min views1 publishedJul 6, 2026

Runs in your browser

no API call

An embedding model in 7 MB.

Runs on your CPU. No API.

Drop it in, embed text in milliseconds, and never call a server.

Runs in your browser

no API call

Engine + weights · 7 MB

mini variant · 5 MB

Fast embeddings · ~5 ms

CPU only · no GPU

USE IT

Ships as a single npm package. No model download step, no server.

$
npm install @ternlight/base
⧉
example.js
⧉
js
import { embed, similar } from '@ternlight/base';

similar('easy weeknight dinner ideas', recipes, { topK: 3 });
// → ranked matches · ~5 ms · zero network

EXAMPLE

Search React's docs in your browser. Type a question — powered by @ternlight/mini, the 5 MB tier.

the engine…

── more in #machine-learning 4 stories · sorted by recency
── more on @ternlight 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/ternlight-7-mb-embed…] indexed:0 read:1min 2026-07-06 ·