Skip to the card

Card 107 of 9902026-09-17 issue

Observed arrival · 2026-09-17

Browser LLM Keeps the Model on Your Machine

browser-llm.com Observed source
Editorial interest 84/100 Selection signal · not a rating of the site

A browser-based chat tool that downloads open models and runs inference locally through WebGPU, storing conversations in the browser.

Landing page captured for the 2026-09-17 issue.

Field notes

The project uses WebLLM in the client, WebGPU for token generation, and IndexedDB for browser-local threads. Its model list makes the hardware requirement unusually legible: SmolLM2 360M is offered as a roughly 200 MB smoke test, while Qwen2.5 7B requires about 4.5 GB. The page says multiple models can be cached, but only one is loaded in VRAM at a time.

Observed signals

Read the marks

Editorial observations of this landing page, not a rating.

OpenPublic substance visible
PrettyNotable craft visible
ProPolished or operationally mature
NicheUnusually specific use
ƒJavaScriptBrowser-side code central

One card from the complete issue

Restaurant City, Back on Speaking Terms

345,627 arrived 1,000 judged 990 catalogued Enter the complete issue
browser-llm.com

Landing page observed 2026-09-17. The live site may have changed.