> ## Documentation Index
> Fetch the complete documentation index at: https://gaia-docs.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Show Model Information

> Retrieves detailed information about an installed Ollama model including capabilities and parameters

## Query Parameters

<ParamField query="modelName" type="string" required>
  Name of the model to inspect (e.g., "llama2", "mistral:7b")
</ParamField>

<ParamField query="verbose" type="boolean" default={false}>
  Include verbose model information
</ParamField>

<ParamField query="baseUrl" type="string">
  Optional Ollama server URL (defaults to [http://localhost:11434](http://localhost:11434))
</ParamField>

## Response

<ResponseField name="success" type="boolean">
  Indicates if the request was successful
</ResponseField>

<ResponseField name="capabilities" type="array">
  Model capabilities and features (e.g., \["chat", "completion", "embedding"])
</ResponseField>

<ResponseField name="details" type="object">
  Detailed model information

  <Expandable title="details properties">
    <ResponseField name="parent_model" type="string">
      Parent model name
    </ResponseField>

    <ResponseField name="format" type="string">
      Model format (e.g., "gguf")
    </ResponseField>

    <ResponseField name="family" type="string">
      Model family (e.g., "llama")
    </ResponseField>

    <ResponseField name="families" type="array">
      Model family hierarchy
    </ResponseField>

    <ResponseField name="parameter_size" type="string">
      Number of parameters (e.g., "7B", "13B")
    </ResponseField>

    <ResponseField name="quantization_level" type="string">
      Quantization level (e.g., "Q4\_0", "Q5\_K\_M")
    </ResponseField>
  </Expandable>
</ResponseField>

<RequestExample>
  ```bash cURL theme={null}
  curl --request GET \
    --url 'http://localhost:3000/api/v1/ollama/show-model?modelName=llama2&verbose=true' \
    --header 'Authorization: Bearer <token>'
  ```

  ```javascript JavaScript theme={null}
  const response = await fetch(
    'http://localhost:3000/api/v1/ollama/show-model?modelName=llama2&verbose=true',
    {
      method: 'GET',
      headers: {
        'Authorization': 'Bearer <token>'
      }
    }
  );

  const data = await response.json();
  ```

  ```python Python theme={null}
  import requests

  url = "http://localhost:3000/api/v1/ollama/show-model"
  headers = {"Authorization": "Bearer <token>"}
  params = {
      "modelName": "llama2",
      "verbose": True
  }

  response = requests.get(url, headers=headers, params=params)
  data = response.json()
  ```
</RequestExample>

<ResponseExample>
  ```json 200 - Success theme={null}
  {
    "success": true,
    "capabilities": ["chat", "completion", "generate"],
    "details": {
      "parent_model": "",
      "format": "gguf",
      "family": "llama",
      "families": ["llama"],
      "parameter_size": "7B",
      "quantization_level": "Q4_0"
    }
  }
  ```

  ```json 401 - Unauthorized theme={null}
  {
    "success": false,
    "error": "Unauthorized"
  }
  ```

  ```json 404 - Not Found theme={null}
  {
    "success": false,
    "error": "Model not found"
  }
  ```

  ```json 500 - Server Error theme={null}
  {
    "success": false,
    "error": "Failed to get model information"
  }
  ```
</ResponseExample>

## Notes

* This endpoint only works for **installed models** (use [List Models](/api-reference/ollama/list-models) to see what's installed)
* The `capabilities` array indicates what the model can do (chat, embeddings, etc.)
* `quantization_level` affects model size and performance
* Use `verbose=true` for additional technical details

## Common Quantization Levels

* **Q4\_0**: 4-bit quantization, smallest size, lower quality
* **Q5\_K\_M**: 5-bit medium quality
* **Q8\_0**: 8-bit quantization, larger size, higher quality