Use Ollama in Kilo Code

Steps

1. 1
   Step 1.

   Make sure Ollama is running.

   Terminal

   Copy

   ollama serve

2. 2
   Step 2.

   In a second terminal, pull a model.

   Terminal

   Copy

   ollama pull qwen3-coder:30b

3. 3
   Step 3.

   VS Code: open Settings (gear icon) and go to the Providers tab to add Ollama. No API key is needed. The extension stores this in your kilo.json config file.

4. 4
   Step 4.

   CLI: config file (~/.config/kilo/kilo.json or ./kilo.json).

   JSON

   Copy

   {
     "provider": {
       "ollama": {
         "baseURL": "http://localhost:11434/v1",
       },
     },
   }

5. 5
   Step 5.

   Then set your default model.

   JSON

   Copy

   {
     "model": "ollama/qwen3-coder:30b",
   }

6. 6
   Step 6.

   Set Context Window Size (num_ctx) in the API Provider settings; Kilo says you need at least 32k for decent results.

7. 7
   Step 7.

   If a model does not appear in the picker, register it as a custom model.

   JSON

   Copy

   {
     "model": "ollama/my-finetune:latest",
     "provider": {
       "ollama": {
         "models": {
           "my-finetune:latest": {
             "name": "My Fine-tuned Model",
             "tool_call": true,
             "limit": {
               "context": 32768,
               "output": 8192,
             },
           },
         },
       },
     },
   }