Health check: whether the Ollama server is reachable and its version. Use this as a precondition before other tools if you're unsure whether Ollama is running.

List locally-installed models: name, size in bytes, digest, modified timestamp, family (e.g. llama), parameter size (e.g. 8.0B), and quantization level (e.g. Q4_K_M).

List models currently loaded into VRAM with their size, VRAM footprint, and expiry timestamp. Empty list means Ollama is idle.

Show detailed information for a specific model: modelfile excerpt, parameters, template, capabilities, architecture details, quantization level.

Run a one-shot text completion against a local model (non-streaming). Returns the full response text plus timing and tokens/second.

Run a chat completion against a local model with message history (non-streaming). Returns the assistant's reply plus timing.

Download a model from the Ollama registry. Blocks until complete — can take a long time for multi-GB models. For very large pulls, prefer ollama pull in a terminal where you can watch progress.

Delete a locally-installed model. Does not affect the remote registry copy. Free the disk space of a model you no longer need.