Gollama is a command-line and TUI tool for macOS and Linux designed to simplify the management of Ollama models. It offers interactive features for listing, inspecting, deleting, copying, and pushing models, with optional integration for LM Studio.

How It Works

Gollama leverages Go and the Charm library for its TUI, providing an interactive interface for model operations. It interacts with the Ollama API to fetch model metadata, perform actions, and manage model files. Key features include sorting, filtering, editing Modelfiles, and estimating VRAM usage for different model configurations and context lengths.

Quick Start & Requirements

• Install via go install github.com/sammcj/gollama@HEAD.
• Requires Go.
• Official documentation: https://github.com/sammcj/gollama

Highlighted Details

• Interactive TUI for model management with customizable hotkeys.
• VRAM estimation tool for Ollama and Hugging Face models, including quantisation analysis.
• "Spit" functionality to copy models to remote hosts.
• LM Studio integration for linking models.
• Customizable themes and logging.

Maintenance & Community

• Active development with contributions from multiple individuals.
• Project is open for contributions via pull requests.

Licensing & Compatibility

• MIT License.
• Permissive license suitable for commercial use and integration with closed-source projects.

Limitations & Caveats

• The project is in active development, with some reported bugs and missing features.
• LM Studio linking requires admin privileges on Windows.
• Docker container and editor integration are experimental features.