Ollama's New Claude Toggle Lets You Run Local Models Inside Claude Desktop
dr_cintas · x · 2026-08-29
Ollama launched a Claude toggle that lets you use your own local models inside the Claude Desktop UI.
Setup:
- Open Ollama, go to Apps, toggle Claude on — Ollama configures the gateway for you.
- Pick any local or Ollama-cloud model in Ollama Settings → Apps, then hit Restart Claude.
- Toggle off to restore the Anthropic setup.
On privacy: prompts with a local model stay on your machine; telemetry is off by default and Ollama cloud runs zero data retention. If the model picker is empty, you can point Claude Desktop's third-party inference at http://127.0.0.1:11434. The author uses this when a task fits a local coder but they still want the Claude Desktop UI.
Related event: Ollama Adds Claude Integration for Local Models in Claude Desktop(2 posts)→
More from coding & agent
- Dev Hooked on Codex Builds a Pet 'Bee' with CoreWeave and Weights & Biases — wandb · 2026-08-29
- Foleo: Local Mac Workspace for Agent-Generated Files with Indexing — joshgonsalves_ · 2026-08-29
- Chamath: Long-horizon tasks and complex problems are still a 'joke' for agents — rohanpaul_ai · 2026-08-29
- The Hidden Cost of 'Relational Buffering' in AI Interactions — mb3rtheflame · 2026-08-29
- LangChain shares how Clay scales agent evals to 300M+ runs per month — LangChain · 2026-08-29
- GLM-5.3-Flash writes Blender script for automotive museum live — mishig25 · 2026-08-29