Ollama
by Ollama · open-source · Last verified 2026-03-17
Tool for running open-source LLMs locally on your machine with a simple CLI interface. Provides one-command model downloads, GPU acceleration, and an OpenAI-compatible API for local AI development.
https://ollama.com ↗B+
B+—Good
Adoption: AQuality: AFreshness: A+Citations: B+Engagement: F
Specifications
- License
- MIT
- Pricing
- open-source
- Capabilities
- local-inference, model-management, gpu-acceleration, openai-compatible-api, custom-models
- Integrations
- langchain, llamaindex, continue-dev, aider
- Use Cases
- local-development, privacy-sensitive-inference, offline-ai, prototyping
- API Available
- Yes
- SDK Languages
- python, typescript, go
- Deployment
- desktop, docker, self-hosted
- Rate Limits
- N/A (local, hardware-limited)
- Data Privacy
- Fully local; no data sent externally
- Tags
- local-inference, desktop, model-runner, privacy
- Added
- 2026-03-17
- Completeness
- 100%
Index Score
71.1Adoption
88
Quality
82
Freshness
92
Citations
78
Engagement
0