Claude Desktop integration with Ollama enables local and cloud model switching

TL;DR

Ollama adds built‑in support for Claude Desktop, allowing developers to toggle Claude on or off and seamlessly switch between Claude, Anthropic cloud models, and any local or cloud model hosted in Ollama, all with zero data telemetry.

Immediate benefit: one‑click model switching

  • Enabling Claude in the Ollama UI automatically configures a third‑party gateway, so no manual API keys or network settings are required.
  • Users can flip a toggle to turn Claude on, then select any model—local or cloud—from Ollama’s model list.
  • Turning Claude off restores the previous Claude configuration, preserving existing workflows.

How to connect Claude Desktop to Ollama

  1. Open the Ollama application and select the Claude option.
  2. Activate the Claude toggle; Ollama will provision the gateway automatically.
  3. The integration is ready; you can now pick any model from the drop‑down menu shown in the settings screen.

Ollama settings showing the Claude app toggle

While Claude is active, the model selector lets you choose among all models available in Ollama, whether they run locally on your machine or are hosted in Ollama’s cloud.

Ollama model selection for Claude

Supported usage scenarios

  • Open models for coding and research – Run community‑released models directly on your hardware for low‑latency tasks.
  • Cloud models for larger workloads – Switch to Anthropic’s hosted Claude or other cloud offerings when you need more compute.
  • Hybrid workflows – Mix and match local and cloud models within a single Claude Desktop session.

Frequently asked questions

Will my prompts or data be sent to Anthropic or Ollama? No. Telemetry is disabled by default, and Ollama enforces a strict Zero Data Retention policy for all models, whether accessed locally or via the cloud.

Can I continue to use Anthropic models? Yes. You can toggle between Anthropic‑hosted Claude and Ollama‑hosted models from the same settings page.

Can I use my own local models with this integration? Yes. Configure a local model on the Settings page and select it for Claude’s backend.

Implications for developers

  • The integration reduces friction for teams that want to experiment with both proprietary Claude models and open‑source alternatives without changing their development environment.
  • Zero‑data‑retention guarantees help organizations meet privacy and compliance requirements while still leveraging powerful LLM capabilities.
  • By exposing a unified UI, Ollama encourages broader adoption of local inference, potentially lowering cloud costs and latency for iterative coding tasks.

Getting started

  1. Install or update Ollama to the latest version.
  2. Open the Settings pane, enable Claude, and choose your preferred model.
  3. Begin prompting Claude Desktop as usual; the underlying model will be routed through Ollama.

This post summarizes the official Ollama announcement dated 2026‑08‑25.

Sources

Related

  • Dispatch
    Ollama v0.14.0: Anthropic API Compatibility and Claude Code Support

    Ollama v0.14.0 introduces compatibility with the Anthropic Messages API, enabling the use of Claude Code and other Anthropic SDK applications with local and cloud open-source models.

  • Project
    Prorise-cool/Claude-Code-Multi-Agent

    Claude Code Multi‑Agent is an open‑source framework that gives Anthropic’s Claude Code project awareness and expert‑agent capabilities. It uses a Python Hook system and a locally‑run Ollama model to automatically detect the codebase type, analyse user intent, load 300+ domain‑specific “Skills” (backend, frontend, testing, security, etc.), and enforce automatic documentation (DEVELOPMENT.md, KNOWLEDGE.md, CHANGELOG.md). After cloning, installing Ollama, a model, and uv, you drop your project into the repo and Claude Code instantly knows its context, suggests appropriate tools, and can be driven with slash commands like `/backend‑specialist` or workflow commands such as `/kiro/spec`. Key points: - Zero‑config start; all configuration lives in `.claude/settings.json` and `prompts.json`. - Hooks run on session start, user prompt, tool use, etc., handling project detection, intent analysis, and doc updates. - Skills are defined by `SKILL.md` files and are auto‑discovered. - Works entirely locally (no external API), integrates with Git, and is MIT‑licensed. Ideal for developers or small teams who want a reproducible, on‑premise AI coding assistant.

  • Dispatch
    Claude for Apple Foundation Models Integration

    Anthropic has released a Swift package allowing Claude to be used as a server-side language model within Apple's Foundation Models framework, providing a unified API for switching between on-device and cloud-hosted models.

  • Dispatch
    Ollama launch command release

    Ollama has introduced the 'ollama launch' command in version 0.15+, allowing users to set up and run coding tools like Claude Code and OpenCode without manual environment variables or configuration files.

  • Dispatch
    Ollama adds Subagents and Web Search to Claude Code

    Ollama now supports subagents and web search within Claude Code, allowing models to run parallel tasks and access real-time information without requiring MCP servers or API keys.