Auryn models · forged by Potara · certified honest
AI that never leaves your building.
Trained on your work. Proven better at it.
Healthcare, legal, finance, and defense can't send their data to a hosted API. The answer is a model that runs on your own hardware, fine-tuned on your own domain, that never phones home. Potara forges it; Auryn is the model; the QPU certificate is the proof it's honest.
Proof, not promises — Auryn-Claims-1.5B
EDI accuracy 0.36 → 1.00
2.99× smaller (986 MB Q4)
runs on an 8 GB GPU
Base Qwen2.5-1.5B (Apache-2.0) · trained on public X12 format · no PHI.
Measured on a 14-task EDI eval (small sample; scorecard is public). Size win is from Q4 quantization. Aimed at the Swoosh.care (HIPAA) domain. Any Auryn eval sample can be drawn on quantum hardware so it's provably not cherry-picked — see the certify-the-test option.
1
InterviewA chat builds your calibration set: what you do, your tasks, examples. It splits skills (train) from facts (retrieve).
2
Fuse on your hardwareMerge + calibration-prune + light QLoRA on your own GPU (data never leaves), or our zero-idle cloud. Facts stay fresh via a retrieval harness.
3
Certify the testOptionally draw the eval sample on real IBM Quantum hardware, so the test set is provably not cherry-picked. Verifiable randomness & provenance only — it does not change the model's quality, size, or speed.
4
Run & re-fuseExport to Ollama, runs local. When a better base drops, re-apply your profile in one click — your investment compounds.
What can your GPU actually run?
Plans
On BYO-GPU, fusion runs entirely on your hardware — your data never leaves your building (the compliance play). On the Cloud tier your data goes to our GPU workers for the job (job-based, deleted after) — for teams without that constraint. QPU certification is a +$10 add-on.
Loading plans…