Qwen-Code: Ollama Ignores num_ctx from settings.json

If you're running Ollama behind an OpenAI-compatible endpoint and setting num_ctx in your client's config, you may notice Ollama still loads the model with only 32k context. This is a silent failure — no errors, just ignored parameters.

Why It Happens

Ollama's /v1 OpenAI-compatible layer only forwards standard OpenAI parameters. Native Ollama options like num_ctx need to be passed inside an options: {} object in the raw request body. Most OpenAI-compatible clients don't do this, so the parameter is quietly dropped and Ollama falls back to the model's default context size.

The Fix

Bake num_ctx directly into the model via a custom Modelfile. This sidesteps the client entirely.

1. Export the existing Modelfile:

ollama show qwen3.6:27b --modelfile > qwen_custom.Modelfile

2. Add or update the num_ctx parameter in the file:

PARAMETER num_ctx 262144

3. Create a new model from it:

ollama create qwen3.6-256k -f qwen_custom.Modelfile

4. Update your client config to point to the new model name, then verify:

ollama ps

The context size shown in ollama ps should now reflect 262144 instead of 32768.

Qwen-code CLI: Use Qwen 3.6 plus from OpenRouter

I qwen code CLI you can use models from OpenRouter or other providers. For example, to use Qwen 3.6 plus modify your .qwen/settings.json as follows: "env": {
"OPENROUTER_API_KEY": "your-openrouter-api-key"
},
"modelProviders": {
"openai": [
{
"id": "qwen/qwen3.6-plus",
"name": "Qwen3.6-plus (via OpenRouter)",
"envKey": "OPENROUTER_API_KEY",
"baseUrl": "https://openrouter.ai/api/v1",
"generationConfig": {
"timeout": 120000,
"maxRetries": 3,
"samplingParams": {
"temperature": 0.7
}
}
}
]
}

More here.