IzwiIzwi

izwi serve

izwi serve

Start the Izwi inference server.

Synopsis

izwi serve [OPTIONS]

Description

Launches the HTTP API server that powers all Izwi functionality. The server provides:

  • REST API endpoints (OpenAI-compatible)
  • Web UI (unless disabled)
  • Model management
  • Real-time inference

Options

OptionDescriptionDefault
--mode <MODE>Startup mode: server, desktop, webserver
-H, --host <HOST>Host to bind to0.0.0.0
-p, --port <PORT>Port to listen on8080
-m, --models-dir <PATH>Models directoryPlatform default
--max-batch-size <N>Maximum batch size8
--metalEnable Metal GPU (macOS)—
-t, --threads <N>Number of CPU threadsAuto
--max-concurrent <N>Max concurrent requests100
--timeout <SECONDS>Request timeout300
--log-level <LEVEL>Log levelwarn
--corsEnable CORS for all origins—
--no-uiDisable the web UI—

Modes

Server Mode (Default)

Starts only the HTTP server:

izwi serve izwi serve --mode server

Access at http://localhost:8080

Desktop Mode

Starts the server and opens the native desktop application:

izwi serve --mode desktop

Web Mode

Starts the server and opens the web UI in your default browser:

izwi serve --mode web

Examples

Basic server

izwi serve

Custom port

izwi serve --port 9000

With Metal acceleration (macOS)

izwi serve --metal

Custom models directory

izwi serve --models-dir /path/to/models

Production settings

izwi serve \\ --host 0.0.0.0 \\ --port 8080 \\ --max-concurrent 200 \\ --timeout 600 \\ --log-level info

Development mode

izwi serve --cors --log-level debug

Environment Variables

VariableEquivalent Option
IZWI_HOST--host
IZWI_PORT--port
IZWI_MODELS_DIR--models-dir
IZWI_USE_METAL--metal
IZWI_MAX_BATCH_SIZE--max-batch-size
IZWI_NUM_THREADS--threads
IZWI_MAX_CONCURRENT--max-concurrent
IZWI_TIMEOUT--timeout
RUST_LOG--log-level
IZWI_SERVE_MODE--mode

Graceful Shutdown

Press Ctrl+C to gracefully shut down the server. Active requests will complete before shutdown.

See Also