TOOLORA / Local reading edition
LM Studio
Load local language models for chat and document Q&A, or serve inference to other applications on your computer.
Overview
LM Studio’s local-model client downloads or imports models and loads them for on-device chat. Attach documents to a conversation: short files enter the context directly, while longer ones can use retrieval-augmented generation. A local server exposes native and compatible APIs to applications. Downloaded-model inference and document processing can work offline; discovery, runtime downloads and updates need connectivity. Model support depends on format, memory and hardware.
- Company country / region
- United States · Company headquarters
Official sources and references
- Official websitehttps://lmstudio.ai/docs/app
- Documentationhttps://lmstudio.ai/docs/app/basics/rag
- Documentationhttps://lmstudio.ai/docs/developer/core/server
Descriptions summarize public information; consult official websites for features, pricing and regional availability.