LM Studio · The default way a normal person runs a model on their own hardware — and, as of this year, a local-first company that has started selling hosted inference, which is the direction's central trade-off happening inside one product.

A desktop app that downloads open models and runs them on your own machine — llama.cpp and MLX under the hood, a chat interface on top, and a local OpenAI-compatible server for your own code. That description is now half the company. The flagship has become Bionic, "an agent made for open models, natively local", and the site sells US-hosted cloud inference alongside it. Around them sit LM Link (talk to models on your Mac from your phone, up to 5 devices), llmster (a headless daemon for servers, cloud instances and CI), the LM Studio Hub, a CLI (lms), and JS/Python SDKs.

Sector

Local & on-device AI

On the roster since

15 Sept 2026