Ollama's Cloud models can now be used inside Claude Desktop
Ollama's Cloud models can now be used inside Claude Desktop
From: Ollama
To: tjphuhs@gmail.com
Account: tjphuhs@gmail.com
Date: 5/5/2026, 12:03:14 AM
Gmail ID: 19df64dec764755d
Thread ID: 19df64dec764755d
Raw Path: /Volumes/Storage Drive/Homelab_Apps_storage/mcp-server/backups/email/tjphuhs@gmail.com/2026/2026-05-05/20260505-040314-19df64dec764755d.eml
Snippet
Ollama 0.23 now supports Claude Desktop's built-in third party inference. This allows all models from Ollama's Cloud to be available for use within Claude Cowork and Claude Code from Claude
Body
Ollama 0.23 now supports Claude Desktop’s built-in third party inference.
This allows all models from Ollama's Cloud to be available for use within Claude Cowork and Claude Code from Claude Desktop.
https://docs.ollama.com/integrations/claude-desktop
Get started
Download Ollama 0.23 [https://ollama.com/download], then run:
ollama launch claude-desktop
You will be prompted to create an Ollama API key [https://ollama.com/settings/keys]. After setup, Claude Desktop will
automatically discover all available Ollama Cloud models.
Choosing a model
Ollama's cloud models will appear automatically in the model selector
https://docs.ollama.com/integrations/claude-desktop
For difficult coding and co-working tasks, the following models are recommended:
* kimi-k2.6
* qwen3.5
* minimax-m2.7
* glm-5.1
For those who don't yet have a paid subscription with Ollama's cloud, choose a model that supports reliable tool calling and
agentic behavior:
* nemotron-3-super
* gemma4:31b
Restoring to Claude models
To restore the default Claude profile, use --restore:
ollama launch claude-desktop --restore
If you have any feedback, please directly reply to this email or join Ollama's Discord channel [https://discord.gg/ollama].
❤️ Ollama
You are receiving this email because you opted-in to receive updates from Ollama
Ollama, 744 High Street, Palo Alto, CA 94301
Unsubscribe [https://app.loops.so/unsubscribe/cmos3s85fbud101909xh60dg5/216d2cca88aefc02547b710588ec62abef41838269eb2884d074706e4153ddbfd618b9e7ee9e47fde92f1ae4607daa5dee48693e6cdeb25a7d5d838e]