MicroLLM lab - tiny LLMs, Q4, in your browser

Lobsters·1 points·dimonomid·1 day ago·stateofutopia.com

Run Q4 small language models entirely in the browser with WebGPU. Chat, benchmark, and compare PetitGPT, SmolLM2, and friends on-device.

Read the full article at stateofutopia.com →

#browser #lab #tiny #llms #microllm #tiny llms #microllm lab #vibecoding

Related stories

MicroLLM Lab – Try 7 tiny LLM's in the browserstateofutopia.com
Hacker News · 278 points · 2 days ago
Show HN: Public Browser MCP – +48% speed -33% token/session vs. AgentBrowsergithub.com
Hacker News · 1 points · 6 days ago
Show HN: StarSkirmish, an arena where LLMs create StarCraft Brood War botsstarskirmish.com
Hacker News · 3 points · 4 days ago
Lobsters: Rename vibecoding to llms (Greasemonkey script)greasyfork.org
Lobsters · 75 points · 6 days ago
Every Single-Page App Is a Worse Browser Running Inside a Browserhypermedia.lol
Hacker News · 1 points · 9 days ago
Nodd – Tiny, use-case-specific decision models that can run in browsermichaljach.github.io
Hacker News · 1 points · 3 days ago

Related topics

game143 ai2028 x2f300 jev349 text102 agents430 app219 real143 free199 open source161 tools95 every136