We train small AI models you own.
Trained on your work. Running offline on your machine. No meter, no account, no data out.
a third of the size · the same answers · yours to keep
At a glance
Measured, not promised.
Measured on Qwen3-1.7B · VALIDATED · Methods
Products
Etch trains it. Edge runs it. Fleet controls your agents.
Torad Etch
Describe the model you need. Etch builds the pipeline, trains on your GPU, and you keep the weights.
Torad Edge
Runs your model offline on hardware you already own. No per-token bill, no account, no round trip.
Torad Fleet
Claude, Codex, and Grok work in one repository without overwriting each other.
Kandi built / app coming
A festival guide running an Etch-trained model offline on the phone. Built with Etch and Edge.
All apps →Benchmarks
A third of the size. The same answers.
We ask the original and the shrunk model the same questions and score how alike the answers are. That score is the A score from 0 to 1.00 for how alike two models' answers are. 1.00 means identical.: 1.00 means identical.
Similarity to the full-size original
VALIDATEDdial · .80 to 1.00needle · 0.9998, oursticks · .85 and .91, the static methods
870 MB vs 2.7 GB · 238 vs 267 tok/s · Methods · All benchmarks
How it works
Train it once. Run it on hardware you own.
A · CPT, SFT, RLB · serves offlineC · the weight file
Why it matters
A model you own cannot be taken away.
The AI you rent is metered, logged, and can change without warning. A model you own is none of those things.
Get started
Get the model that knows your work.
etch strike my-model.tq4
✓ model saved · yours to keep
edge serve --offline
✓ listening on localhost · 0 bytes left the machine