Model Releases
You can now run Claude Desktop fully on local models with one toggle. Open @ollama on, pick a model. Cowork and Claude Code inside the deskt…
You can now run Claude Desktop fully on local models with one toggle. Open @ollama on, pick a model. Cowork and Claude Code inside the desktop app run on it. Flip it off, you're back to Anthropic. Why
You can now run Claude Desktop fully on local models with one toggle. Open @ollama on, pick a model. Cowork and Claude Code inside the desktop app run on it. Flip it off, you're back to Anthropic. Why I care? my whole Obsidian second-brain setup runs through Claude Code. That now works on a local model with zero data leaving the machine. Steps below 👇
Related
- Documentation https://docs.ollama.com/integrations/claude-desktop
- 🤯 Ollama now supports Claude Desktop via Claude’s built-in third party inference. ollama launch claude-desktop This allows all models from …
- At any point in time, you can safely resume to using Anthropic's models: ollama launch claude-desktop --restore
Source: Ollama (X) | 2026-08-26