You can now use Ollama cloud models inside Claude Desktop

ByIvan Jenic

Ollama now lets you run its cloud models inside Claude Desktop, including Claude Cowork and Claude Code, with a single command.

ollama logo

Ollama just added Claude Desktop support, letting users run Ollama Cloud models directly inside Claude’s desktop app. That includes Claude Cowork for autonomous file and desktop tasks, and Claude Code for coding sessions, both switching over to Ollama’s model roster instead of Anthropic’s.

Setup is a single command:

ollama launch claude-desktop

Before running it, you need an Ollama API key set in your shell:

export OLLAMA_API_KEY=your_api_key

After that, Claude Desktop discovers available Ollama Cloud models automatically. Models like Kimi K2.6 and Qwen variants show up inside Cowork and Claude Code without any additional configuration.

What works and what doesn’t:

  • Claude Cowork: Fully supported with Ollama Cloud models, including autonomous file and app tasks
  • Claude Code: Supported inside Claude Desktop with the same cloud models
  • Subagents: Supported, with an option to have subagents inherit the current model
  • Web search and extensions: Not supported yet

Switching back to standard Anthropic Claude takes one command: ollama launch claude-desktop --restore. If Claude Desktop is already running, add --yes to approve the restart automatically.

The timing is worth noting. Anthropic recently removed the ability to use Claude subscription limits for third-party tools, a move that affected OpenClaw users and others running agents on top of their subscriptions. This Ollama integration goes the other direction: it uses Claude’s own interface while routing inference through Ollama Cloud, which means it draws on Ollama’s capacity rather than Anthropic’s.

Source: Ollama

RunPod
RunPod

If you need on-demand GPUs for training, fine-tuning, inference, or running open-source models, give RunPod a try.

  • Available hardware: H100, H200, A100, L40S, RTX 4090, RTX 5090, and 30+ more
  • Cost: significantly cheaper than AWS or GCP, billed per second, no contracts
  • Setup: spins up in under a minute, 30+ regions worldwide
Try RunPod →
Affiliate disclosure: We may earn a commission if you sign up via our link, at no extra cost to you.
Efficienist Newsletter

Get the core business tech news delivered straight to your inbox. We track AI, automation, SaaS, and cybersecurity so you don't have to.

Just read what you want, and be done with it.

Read Next