Private AI Lab — Travis Smith

What I built

Launched and operating on an RTX 6000 Pro and Threadripper Pro 9965WX, using open-source models for private, on-device inference and local processing.

Architecture sketch

  RTX 6000 Pro + Threadripper Pro 9965WX
                    │
                    ▼
           open-source models
                    │
                    ▼
        private inference / local processing

Local ownership

Operate open-source models on owned hardware, keeping model inference local and controlling the processing environment. The deployment is designed for end-to-end local workflows.

Implementation scope and verification

Launched and operating on an RTX 6000 Pro and Threadripper Pro 9965WX, using open-source models for private, on-device inference and local processing.

Operate open-source models on owned hardware, keeping model inference local and controlling the processing environment. The deployment is designed for end-to-end local workflows.

Deployment status and hardware were confirmed by Travis Smith. The portfolio source review did not independently audit network egress, storage, access controls or third-party tools; those boundaries determine end-to-end privacy for each workflow.

About the evidence