GitHub · by RJMSWD
A Jev-style conversion of Qwen-3.5-4B, at 0.169 s per frame.
The Qwen-3.5-4B vision-language model converted to work like Jev, reaching 0.169 seconds per frame for recognition. The author notes the same approach transfers to the other Qwen models.
Repository created Sep 21, 2026. Counts read from the GitHub API on Oct 15, 2026, and they move daily — quote them with the date.
Cua
@trycua
1/ Introducing CUA-S1: a family of System One Models, small, specialized, and built for computer use. Today we're open-sourcing CUA-S1-FORMS, the first in the family: github.com/trycua/cua
Vincent Wang-Maścianica
@vinnylarouge
I reverse-engineered a jev-like architecture given its type. You can find the repo here to train your own jevlikes: github.com/vinnylarouge/j…
GitHubOpen source
Eric Zhang
@ekzhang1
Inspired by @typesafeai , here is a Jev-compatible public API to play with It runs a comparable open model (Qwen3.6-35B-A3B), and just uses SGLang radix cache to preserve the prefill reuse / really fast parallel systemone generation - 64 tasks in <1s. github.com/ekzhang/openje…
