Skip to content
Torad. LAB / 001
Talk to us
Torad Labs · the lab the research is the company

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 →
punishment reward
The training signal is reward. Punishment is not used.
How the engine works → Read the research →

Milestones

From the refusal to what ships next.

January 2026 to now, dated.

  1. Jan 2026The refusal

    We saw distress patterns in a trained model and refused to build that way. The lab was founded that month.

  2. 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.

  3. May 2026Kandi ships, end to end

    A festival companion running a model we trained with Etch, fully on the phone, offline.

  4. 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.

  5. 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.

Your brief

research is the company · runs offline · Torad Labs