Built with Open reimplementations
jev-on-a-laptop
Unofficial study: Jev-style parallel typed decisions on stock 1.5B-8B models on an Apple Silicon laptop. Benchmarks, research notes, and a Hugging Face Space demo.
25 ★ on GitHub
What it is
Unofficial research repo. Not affiliated with TypeSafe AI. This is a hands-on study of the parallel constrained decoding idea behind Jev — the "System One" model launched by Diogo Almeida's TypeSafe AI in Sep 2026 — reproduced on a stock, untrained small model, on an Apple Silicon laptop.
Getting started
From the README:
git clone https://github.com/rorshopping/jev-on-a-laptop
cd jev-on-a-laptop
./setup.sh # creates .venv, installs mlx-lm, clones the upstream engine
./run_benchmark.sh # default: Qwen2.5-1.5B-Instruct-4bitWhere the decision sits
jev-on-a-laptop runs its own weights or its own runtime rather than calling a hosted API, so its decisions do not depend on a vendor being up or on a key being funded. The trade is that the model is now yours to keep current.
Models it references: jev, Qwen-2.5-1B-RLCD, Qwen-2.5-1B-RLCD.
How active it is
Created 2026-09-16, last pushed 2026-09-17, 25 stars and 1 forks when we read it on 2026-11-02. Everything in this category is weeks old at most, so a stale push date means something different here than it would on a mature project. Check the repository before you depend on it.
Find out what your data actually supports
We turn your historical decisions into a frozen test set, then tell you which model, which threshold, and how much of it you can safely automate.