Observed arrival · 2026-10-11
WebSLM runs small language models in your browser
WebSLM offers a browser-based way to download and run open language models locally, using WebGPU when available or the CPU otherwise.
○Open
⊠Login
$Paid
†Ads
✦Pretty
●Pro
◎Niche
◉Human
⚑Risk
ƒJS
- For
- People drafting sensitive text on ordinary laptops
- Worth noticing
- The site reports LFM2.5 1.2B running at 6.6 tokens per second on a laptop with integrated graphics.
Field notes
The page lays out a three-step workflow: choose a model, download it once, then run it in the browser. Device checks cover WebGPU, memory, and storage; model entries show size and licence, and models can be removed to reclaim space. For larger models, the page describes switching to a llama.cpp server on the user's own computer and sending messages only to the chosen address.
Observed signals
Read the marks
Editorial observations of this landing page, not a rating.
○OpenPublic substance visible
⊠LoginAccess appeared gated
✦PrettyNotable craft visible
●ProPolished or operationally mature
◎NicheUnusually specific use
One card from the complete issue