preowned turns macOS built-in Apple models into an OpenAI-compatible local API
pcuenq · x · 2026-10-28
Developer mattt released preowned, an open-source local server that exposes the models shipped inside macOS (LLM, image generation, transcription, translation, speech synthesis) behind an OpenAI-compatible API.
- Point any OpenAI client at preowned and chat (streaming + structured output), embeddings, transcription, translation, and speech all run locally on your Mac
- Requests for gpt-4o or whisper-1 route to Apple's built-in counterpart; any API key works
- A screenshot shows locally listed models including apple-foundation-model, apple-nl-embedding, apple-speech-transcriber, and apple-speech-synthesizer
- Limitations: no tool calling, no Responses API
More from Infra
- Amazon, Google and Microsoft both buy from Anthropic and sell it $269B of compute — YvesMulkers · 2026-10-28
- AMD and Meta deepen partnership: Helios rackscale systems deployed for Meta's superintelligence infra — wkmyrhang · 2026-10-28
- DeepSeek on $75K of hardware: 2,120 tok/s decode at 16 concurrent sessions — victormustar · 2026-10-28
- Back-of-envelope math: 120B DeepSeek-class tokens per person by end of 2027 — bookwormengr · 2026-10-28
- Google TPUs to Run on Oracle Cloud, Making OCI the First Outside Hyperscaler With TPU — rseroter · 2026-10-28
- Arm EVP Mohamed Awad on why agents need their own CPU, a $251B server CPU market by 2030 — BenBajarin · 2026-10-28