This is an old revision of the document!
Run local AI models on macOS

install Ollama
install OpenAI codex
Run codex with Ollama using local AI models

$ ollama list
NAME                    ID              SIZE     MODIFIED   
muse-glimmer:30b-mlx    015fa21845be    19 GB    2 days ago
$ ollama launch codex
Select model for Codex CLI: Type to filter...                                                       
                                                                                                    
  Recommended                                                                                       
    glm-5.3-flash:cloud                                                                             
      Fast reasoning for coding and agentic workloads with 1M context and native image understanding
    glm-5.3:cloud                                                                                   
      Long-horizon coding and agentic engineering with deep reasoning and a 1M context              
    deepseek-v4.1-flash:cloud                                                                       
      Fast coding and agentic tool use with 1M context and native image understanding               
    gemma4:31b-cloud                                                                                
      Agentic workflows and multimodal reasoning                                                    
    gemma4:26b                                                                                      
      Agentic workflows and multimodal reasoning, ~19GB, (not downloaded)                           
                                                                                                    
  More                                                                                              
  ▸ muse-glimmer:30b-mlx