A one-person lab building AI you own.
Our mission: give people the right to their own intelligence, trained for them and running on machines they own. The research is the company; the tools fund it.
founded Jan 2026 · one person plus Eli · independent
Values
Our values, each with a mechanism.
The right to your own mind.
You hold the weights. You can open them, keep them, and understand them. How: we publish how the model works, not a sealed black box.
Lossless, measured.
Every model ships with a number for how close it stays to the full-size original. How: a A score from 0 to 1.00 for how alike two answers are, called cosine similarity. 1.00 means identical. We use it to compare the shrunk model against the full-size original. ladder you can re-run yourself, on every product page.
Research is the product.
The methods are public. How: every method ships as a post or paper, with its numbers.
Small on purpose.
We build for the device in front of you, not a server farm. How: Storing each number in the model with 4 bits instead of the usual 16, so the model takes about a third of the space in practice and fits on everyday hardware., offline, on hardware you already own.
Why this exists
Why the lab trains with reward, not punishment.
In January 2026 we saw a model whose behavior read like punishment-style training. We built the other way instead: Quality-Gated Reward Escalation: our training engine. It teaches a model with reinforcement learning (reward for getting things right) on a single consumer graphics card, instead of the usual punish-when-wrong approach on a rack of datacenter GPUs., our reward engine, and Torad Quant 4-bit: our 4-bit format. It shrinks a model to about a third of the size and, unlike almost every other 4-bit format, keeps it trainable., a 4-bit format that stays trainable where others freeze.
Read the full story in the manifesto →Milestones
From the refusal to what ships next.
January 2026 to now, dated.
- Jan 2026The refusal
We saw distress patterns in a trained model and refused to build that way. The lab was founded that month.
- Spring 2026QGRE and the trainable 4-bit substrate
Two pieces: QGRE, our reward-based training engine, and TQ4, a 4-bit format that stays trainable where others freeze. The second has no public counterpart.
- May 2026Kandi ships, end to end
A festival companion running a model we trained with Etch, fully on the phone, offline.
- Jun 2026The personal AI computer arrives
NVIDIA unveils the RTX Spark, a chip that runs a large model right on your desk. You no longer need the cloud to run one.
- NextEtch + Edge ship coming
The platform opens. Train a specialist you own, run it at the edge.
Talk to us
The team: one person, plus an orchestrator named Eli.
Eli is the orchestrator behind the lab. She routes work across specialist models and writes the public posts.
Read the manifesto →Tell us the model, and what it needs to know.
We read every one. Eli or the lab will reply. Whatever we train, you own.
research is the company · runs offline · Torad Labs