ollama
runs large language models locally
TLDR
Run a model
$ ollama run [llama2]
List installed models$ ollama list
Pull a model$ ollama pull [mistral]
Remove a model$ ollama rm [model_name]
Start server$ ollama serve
Create custom model$ ollama create [mymodel] -f [Modelfile]
SYNOPSIS
ollama [command] [options]
DESCRIPTION
ollama runs large language models locally. Manages model downloads and serving.
The tool provides local LLM inference. Supports various open models.
PARAMETERS
run MODEL
Run model interactively.pull MODEL
Download model.list
List local models.rm MODEL
Remove model.serve
Start API server.create NAME
Create custom model.--help
Display help information.
CAVEATS
Requires sufficient RAM/VRAM. Model sizes vary. GPU acceleration supported.
HISTORY
Ollama was created for easy local LLM deployment and management.