Ollama
An open-source runtime for running large language models locally on various hardware.
Ollama enables users to deploy AI models without cloud services, supporting hardware like CPU and ROCm for accessible inference. It simplifies local AI workflows for developers and hobbyists, facilitating quick experimentation and integration of LLMs into applications while maintaining data privacy. Its prominence grew with features like the Hermes Agent in v0.21.0, boosting adoption for privacy-focused AI tools.
Category: project · Also: ollama/ollama · Mentioned in 3 Cortex outputs