Detailed Command’s of Ollama

Detailed Command’s of Ollama

Ollama offers various commands to manage and run models effectively across different operating systems. Here is a detailed look at each command with examples:

1. serve
   • Usage: ollama serve
   • Description: Starts the Ollama server.
   • Example: ollama serve
   • Flags:
     • -h, --help: Help for serve.
   • Environment Variables:
     • OLLAMA_HOST: The host and port to bind to (default is 127.0.0.1:11434).
     • OLLAMA_ORIGINS: Allowed origins (comma-separated).
     • OLLAMA_MODELS: Path to the models directory (default is ~/.ollama/models).
     • OLLAMA_KEEP_ALIVE: Duration models stay loaded in memory (default is 5m).
     • OLLAMA_DEBUG: Set to 1 to enable debug logging.
2. create
   • Usage: ollama create MODEL
   • Description: Creates a model from a Modelfile.
   • Example: ollama create custom-model -f myModelfile.yaml
   • Flags:
     • -f, --file string: Name of the Modelfile (default is Modelfile).
     • -q, --quantize string: Quantize model to this level (e.g., q4_0).
   • Environment Variables:
     • OLLAMA_HOST: The host and port or base URL of the Ollama server.
3. show
   • Usage: ollama show MODEL
   • Description: Shows information for a model.
   • Example: ollama show llama3 --parameters
   • Flags:
     • --license: Show license of a model.
     • --modelfile: Show Modelfile of a model.
     • --parameters: Show parameters of a model.
     • --system: Show system message of a model.
     • --template: Show template of a model.
   • Environment Variables:
     • OLLAMA_HOST: The host and port or base URL of the Ollama server.
4. run
   • Usage: ollama run MODEL [PROMPT]
   • Description: Runs a model.
   • Example: ollama run llama3 "Explain quantum mechanics."
   • Flags:
     • --format string: Response format (e.g., JSON).
     • --keepalive string: Duration to keep a model loaded (e.g., 5m).
     • --nowordwrap: Don’t wrap words to the next line automatically.
     • --verbose: Show timings for response.
   • Environment Variables:
     • OLLAMA_HOST: The host and port or base URL of the Ollama server.
5. pull
   • Usage: ollama pull MODEL
   • Description: Pulls a model from a registry.
   • Example: ollama pull llama3
   • Flags:
     • --insecure: Use an insecure registry.
   • Environment Variables:
     • OLLAMA_HOST: The host and port or base URL of the Ollama server.
6. push
   • Usage: ollama push MODEL
   • Description: Pushes a model to a registry.
   • Example: ollama push custom-model
   • Flags:
     • --insecure: Use an insecure registry.
   • Environment Variables:
     • OLLAMA_HOST: The host and port or base URL of the Ollama server.
7. list
   • Usage: ollama list
   • Aliases: list, ls
   • Description: Lists all models.
   • Example: ollama list
   • Flags:
     • -h, --help: Help for list.
   • Environment Variables:
     • OLLAMA_HOST: The host and port or base URL of the Ollama server.
8. ps
   • Usage: ollama ps
   • Description: Lists running models.
   • Example: ollama ps
   • Flags:
     • -h, --help: Help for ps.
   • Environment Variables:
     • OLLAMA_HOST: The host and port or base URL of the Ollama server.
9. cp
   • Usage: ollama cp SOURCE DESTINATION
   • Description: Copies a model.
   • Example: ollama cp llama3 backup-llama3
   • Flags:
     • -h, --help: Help for cp.
   • Environment Variables:
     • OLLAMA_HOST: The host and port or base URL of the Ollama server.
10. rm
    • Usage: ollama rm MODEL [MODEL...]
    • Description: Removes a model.
    • Example: ollama rm llama3
    • Flags:
      • -h, --help: Help for rm.
    • Environment Variables:
      • OLLAMA_HOST: The host and port or base URL of the Ollama server.
11. help
    • Usage: ollama help [command]
    • Description: Provides help for any command in the application.
    • Example: ollama help run
    • Flags:
      • -h, --help: Help for help.