Observed arrival · 2026-11-22
ShareInference turns spare GPU time into model credits
ShareInference says users can contribute GPU compute from a browser tab, then use earned credits through an OpenAI-compatible API for open-weight models.
○Open
⊠Login
$Paid
†Ads
✦Pretty
●Pro
◎Niche
◉Human
⚑Risk
ƒJS
- For
- Open-model developers and compatible GPU owners
- Worth noticing
- The homepage specifies one credit per input token and five per output token, and requires Chrome or Edge with WebGPU for sharing.
Field notes
The page describes a two-sided credit loop rather than a conventional hosted-inference signup: providers contribute browser-based compute, while API users spend credits for access and queue priority. It says the model downloads once and is cached, and lists both REST and streaming API formats. The project identifies its source code as AGPL-3.0; the extracted page does not confirm that inference is currently running.
Observed signals
Read the marks
Editorial observations of this landing page, not a rating.
○OpenPublic substance visible
✦PrettyNotable craft visible
◎NicheUnusually specific use
ƒJavaScriptBrowser-side code central
One card from the complete issue