Ollama Cloud Models Preview

Ollama has launched a preview of Cloud models, allowing users to run massive large language models (LLMs) on datacenter-grade hardware without needing the local hardware capacity to host them. This update enables a seamless transition between local and cloud-based inference while maintaining privacy through a policy of not retaining user data.

High-Performance Hardware for Large-Scale Models

Ollama Cloud provides access to models that are too large to fit on standard personal computers. By offloading the compute to the cloud, users can leverage fast, datacenter-grade hardware while continuing to use their existing local Ollama tools and workflows.

Model Availability and Versioning

To access cloud models, users must be running Ollama v0.12. The following models are currently available in the cloud preview:

  • qwen3-coder:480b-cloud
  • gpt-oss:120b-cloud
  • gpt-oss:20b-cloud
  • deepseek-v3.1:671b-cloud

Integration and API Compatibility

Cloud models are designed to behave like standard local models within the Ollama ecosystem. They integrate with the existing CLI commands such as ollama ls, ollama run, ollama pull, and ollama cp.

API Access Methods

Ollama Cloud models are accessible through multiple interfaces:

  1. OpenAI-compatible API: Cloud models work via Ollama’s OpenAI-compatible API.
  2. Ollama Libraries: Official JavaScript (npm install ollama) and Python (pip install ollama) libraries support cloud models.
  3. Direct API: Models can be accessed directly via the ollama.com API.
  4. cURL: Standard REST calls to http://localhost:11434/api/chat can be used to interact with cloud models after they have been pulled.

Authentication and Privacy

Accessing cloud models requires authentication because the inference compute is hosted on ollama.com. Users must use the following commands to manage their session:

  • Sign In: ollama signin
  • Sign Out: ollama signout

Regarding security, Ollama states that its cloud service does not retain user data to ensure privacy and security.

Sources

Related

  • Dispatch
    Ollama Windows Preview Release

    Ollama has launched a preview version for Windows, enabling users to run, pull, and create large language models locally with native GPU acceleration and API access.

  • Project
    ollama/ollama

    Ollama is a cross‑platform runtime that lets you download and run open‑source large language models locally. It offers a CLI, a REST API (localhost:11434), and official Python/JS SDKs, plus many community integrations (web UIs, LangChain, AutoGPT, etc.). Install with a one‑line script or Docker, then launch models like `ollama run gemma4` or use `ollama launch` to connect to coding assistants or personal bots.

  • Dispatch
    Ollama Web Search and Web Fetch API Release

    Ollama has released a new web search and web fetch API to reduce hallucinations and provide LLMs with real-time web data via REST and library integrations.

  • Project
    taketwo/llm-ollama

    A plugin for the LLM CLI tool that enables seamless integration and interaction with models running on local, remote, or cloud-hosted Ollama servers.

  • Dispatch
    Ollama Coding Models and Integrations Update

    Ollama has introduced cloud access to GLM-4.6 and Qwen3-Coder-480B, alongside updates to Qwen3-Coder-30B and expanded integrations for VS Code, Zed, and Droid.