Linum-AI/pjit-21k

2B-parameter pixel-space text-to-image model (Pyramid-JiT) trained for $21K

Python

1 contributors

Apache License 2.0

Fastest Enterprise AI Gateway for Routing, Governing, and Securing all your AI Traffic

Momentum

How fast Linum-AI/pjit-21k is gaining stars, and where it lands on Trendshift and GitHub Trending

Stars, forks and merged pull requests each day or month, lined up with the repository's rank on Trendshift Trending

Nov 5 – Nov 7, 2026

Stars +9 in 3 days

Forks +0 in 3 days

Merged PRs 0 in 3 days

Trendshift Trendingwhere the repository ranked each day it made the top 25

Not in the Trendshift top 25 in this period

Nov 5Nov 6Nov 7

Stars, forks, merged pull requests and Trendshift Trending rank, by day
Day	Stars gained	Forks gained
Thu, Nov 5, 2026	+0	+0
Fri, Nov 6, 2026	+7	+0
Sat, Nov 7, 2026	+2	+0
Total	+9	+0

Recent discussions about this repository across the web

Nov 71 post
- Two brothers just did something you'd expect from a massive AI lab. They trained their own 2-billion-parameter AI image generator. Their GPU compute bill? Just $21,038. Not a fine-tune of an existing…
  Read full on X, posted by @heynavtoor
  @heynavtoor · x.com
Nov 61 post
- someone trained a decent text-to-image model for $21,038. then open-sourced it. → P-JiT: 2B params, Apache 2.0 weights + code → 8,415 H100-hours total, a real recipe if you want to train your own →…
  Read full on X, posted by @johan_builds
  @johan_builds · x.com