Issue Station
Sign In
Tools hereToolbox

ollama - 💡(How to fix) Fix Codex with ollama won't launch [1 pull requests]

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…

Error Message

base) cognitron@cognitron-workstation:~/Projects/Physics_Projects/Cognitron_MultiRobot_MVP$ ollama launch codex

(base) cognitron@cognitron-workstation:~/Projects/Physics_Projects/Cognitron_MultiRobot_MVP$ ollama launch codex Select model for Codex: Type to filter...

Recommended
kimi-k2.6:cloud
State-of-the-art coding, long-horizon execution, and multimodal agent swarm capability
glm-5.1:cloud
Long-horizon agentic engineering with autonomous execution and sustained iteration
qwen3.5:cloud
Reasoning, coding, and agentic tool use with vision
nemotron-3-super:cloud
Reasoning, coding, and agentic tool use
gemma4:31b-cloud
Agentic workflows and multimodal reasoning
gemma4
Agentic workflows and multimodal reasoning, ~12GB, (not downloaded)
qwen3.6
Agentic software engineering model with multimodal capabilities, ~28GB, (not downloaded)

More
▸ gemma4:31b
ministral-3:3b-cloud

Error loading config.toml: --profile ollama-launch cannot be used while /home/cognitron/.codex/config.toml contains legacy profile = "ollama-launch" or [profiles.ollama-launch] config; move those settings into /home/cognitron/.codex/ollama-launch.config.toml and remove the legacy profile selector/table. See https://developers.openai.com/codex/config-advanced#profiles for more information. Error: exit status 1

Fix Action

Fixed

Code Example

base) cognitron@cognitron-workstation:~/Projects/Physics_Projects/Cognitron_MultiRobot_MVP$ ollama launch codex

(base) cognitron@cognitron-workstation:~/Projects/Physics_Projects/Cognitron_MultiRobot_MVP$ ollama launch codex
Select model for Codex: Type to filter...                                                     
                                                                                              
  Recommended                                                                                 
    kimi-k2.6:cloud                                                                           
      State-of-the-art coding, long-horizon execution, and multimodal agent swarm capability  
    glm-5.1:cloud                                                                             
      Long-horizon agentic engineering with autonomous execution and sustained iteration      
    qwen3.5:cloud                                                                             
      Reasoning, coding, and agentic tool use with vision                                     
    nemotron-3-super:cloud                                                                    
      Reasoning, coding, and agentic tool use                                                 
    gemma4:31b-cloud                                                                          
      Agentic workflows and multimodal reasoning                                              
    gemma4                                                                                    
      Agentic workflows and multimodal reasoning, ~12GB, (not downloaded)                     
    qwen3.6                                                                                   
      Agentic software engineering model with multimodal capabilities, ~28GB, (not downloaded)
                                                                                              
  More                                                                                        
  ▸ gemma4:31b                                                                                
    ministral-3:3b-cloud         



Error loading config.toml: --profile `ollama-launch` cannot be used while /home/cognitron/.codex/config.toml contains legacy `profile = "ollama-launch"` or `[profiles.ollama-launch]` config; move those settings into /home/cognitron/.codex/ollama-launch.config.toml and remove the legacy profile selector/table. See https://developers.openai.com/codex/config-advanced#profiles for more information.
Error: exit status 1
RAW_BUFFERClick to expand / collapse

What is the issue?

when i tried to lauch ollama's latest version 0.24.0 using codex cli it doesn't work ! instead it warns about legacy profiles and even if i edit to remove those ollama add those automatically.

it add this profiles section automatically

' [model_providers.ollama-launch] name = "Ollama" base_url = "http://127.0.0.1:11434/v1/" wire_api = "responses" [profiles.ollama-launch] openai_base_url = "http://127.0.0.1:11434/v1/" model_provider = "ollama-launch" forced_login_method = "api" ,

and its not supported by codex anymore

Relevant log output

base) cognitron@cognitron-workstation:~/Projects/Physics_Projects/Cognitron_MultiRobot_MVP$ ollama launch codex

(base) cognitron@cognitron-workstation:~/Projects/Physics_Projects/Cognitron_MultiRobot_MVP$ ollama launch codex
Select model for Codex: Type to filter...                                                     
                                                                                              
  Recommended                                                                                 
    kimi-k2.6:cloud                                                                           
      State-of-the-art coding, long-horizon execution, and multimodal agent swarm capability  
    glm-5.1:cloud                                                                             
      Long-horizon agentic engineering with autonomous execution and sustained iteration      
    qwen3.5:cloud                                                                             
      Reasoning, coding, and agentic tool use with vision                                     
    nemotron-3-super:cloud                                                                    
      Reasoning, coding, and agentic tool use                                                 
    gemma4:31b-cloud                                                                          
      Agentic workflows and multimodal reasoning                                              
    gemma4                                                                                    
      Agentic workflows and multimodal reasoning, ~12GB, (not downloaded)                     
    qwen3.6                                                                                   
      Agentic software engineering model with multimodal capabilities, ~28GB, (not downloaded)
                                                                                              
  More                                                                                        
  ▸ gemma4:31b                                                                                
    ministral-3:3b-cloud         



Error loading config.toml: --profile `ollama-launch` cannot be used while /home/cognitron/.codex/config.toml contains legacy `profile = "ollama-launch"` or `[profiles.ollama-launch]` config; move those settings into /home/cognitron/.codex/ollama-launch.config.toml and remove the legacy profile selector/table. See https://developers.openai.com/codex/config-advanced#profiles for more information.
Error: exit status 1

OS

Linux

GPU

Nvidia

CPU

AMD

Ollama version

0.24.0

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING

ollama - 💡(How to fix) Fix Codex with ollama won't launch [1 pull requests]