Deploy
On your own hardware
Myles on servers, laptops and GPUs you operate.
Myles runs on hardware you operate: servers, laptops, phones and GPUs, including disconnected and air-gapped networks. Nothing is sent to Launchables. Myles-G runs behind the same Decision API as the hosted endpoint, so code written against one works on the other.
Choosing hardware
| Model | Hardware | Median decision |
|---|---|---|
| Myles-G 31B | One data-centre GPU | 48 ms |
| Myles-G 12B | One workstation GPU | 31 ms |
| Myles-G Edge | Laptop- and phone-class GPUs | 21 ms |
| Myles-400M | Any server CPU, one thread per decision | about 500 ms |
| Myles-150M | A laptop CPU | 196 ms |
| Myles-22M | A browser or a phone | 27 ms |
What you get
- The model weights for your deployment, with their lineage record and measured results.
- For Myles-G, the Decision API server: the same interface as the hosted endpoint, with your own tokens and limits.
- For the CPU models, the model files and help integrating them with your stack.
- Help setting and certifying thresholds on your own decisions.
Licensing
One licence per deployment, monthly or annual, with no per-decision fees. Evaluation licences cover trials. See Licensing.
Request a self-hosted evaluationWe measure Myles on a sample of your own decisions, then you trial it under an evaluation licence.
Use the hosted API insteadMyles-G 12B, hosted by us. Buy credit in the console and get a key.
Security reviews
Ask us for the lineage record, our evaluation method and results, or send your security questionnaire: security questions. See also Assurance.