Launches · Project

Ollama

Ollama runs and serves local models and connects to separately hosted cloud models.

+ Follow

Builder facts

  • Authentication. The local API does not require authentication by default. The hosted endpoint uses an API key, and cloud models accessed through the local server require sign-in. Source ↗
  • Model imports. A Modelfile can import GGUF or supported Safetensors models. Ollama does not quantize GGUF files during import. Source ↗
  • API compatibility. Ollama implements a subset of the OpenAI API, including a stateless Responses endpoint. Source ↗
  • Cloud usage. The cloud service has separate plans and usage credits for hosted inference. Source ↗

Sources checked

Publisher update ·

Ollama 0.40.16 ↗

The Responses endpoint now honors the truncation setting and stops silently truncating input by default.

Change timeline

0 stories

No verified releases in this timeline yet.