Getting started
LocalLMChat is a client for a language-model server that you provide. Before using the app, start a compatible server and make sure your iPhone or iPad can reach it over the network.
Server configuration
In LocalLMChat settings, enter the protocol, host name or IP address, and port for your server. Select the appropriate API type, then use Test Connection to verify that the app can reach the server and retrieve available models.
Supported APIs
LocalLMChat supports OpenAI-compatible Completions and Responses APIs and the LM Studio Chat API. Compatibility with a particular third-party server depends on its implementation of those APIs.
Local network access
If your server is on your local network, iOS may ask for permission for LocalLMChat to access devices on the local network. This permission is required to connect directly to a server on your LAN.
HTTP and HTTPS
LocalLMChat supports both HTTP and HTTPS because many self-hosted inference servers expose HTTP endpoints on local/private networks.
Security: HTTP does not encrypt traffic. Use an HTTP server only on a network you trust or through an encrypted private network/VPN. Use HTTPS when your server provides it.
If a connection fails
- Confirm that the inference server is running.
- Verify the server address, protocol, and port.
- Make sure the device can reach the server's network.
- Check that Local Network access is allowed in iOS Settings when connecting over a LAN.
- Verify that the selected API is supported by the server.
Contact
For additional support, contact Hammurabi Concepts at locallmchat@hammurabiconcepts.com.