> ## Documentation Index > Fetch the complete documentation index at: https://anaconda.com/docs/llms.txt > Use this file to discover all available pages before exploring further. # Models The `.models` accessor provides methods for listing and downloading models. Method Return type Description `.list()` `List[Model]` List all available models `.get('')` `Model` Fetch model metadata and quantizations `.download('/')` `None` Download a quantized model file `.delete('/')` `None` Delete a downloaded model file ## Model class Attribute/Method Type Description `.name` `str` Model name `.description` `str` Model description `.num_parameters` `int` Number of model parameters `.trained_for` `str` Training purpose (for example, 'text-generation', 'feature-extraction') `.context_window_size` `int` Context window length `.quantized_files` `List[QuantizedFile]` Available quantization files `.get_quantization('')` `QuantizedFile` Get a specific quantization by method `.download('')` `None` Download a specific quantization `.delete('')` `None` Delete a specific quantization ## QuantizedFile class Attribute/Method Type Description `.sha256` `str` SHA256 checksum of the model file `.size_bytes` `int` File size in bytes `.quant_method` `str` Quantization method (for example, 'Q4\_K\_M', 'Q8\_0') `.max_ram_usage` `int` Required RAM in bytes `.format` `str` File format (typically 'gguf') `.identifier` `str` Full filename (for example, 'model\_name\_q4\_k\_m.gguf') `.is_downloaded` `bool` Whether the file is downloaded `.is_allowed` `bool` Whether the file is available on this system `.local_path` `Optional[Path]` Local file path (if downloaded) `.download()` `None` Download this quantization file `.delete()` `None` Delete this quantization file ## Downloading models Download a quantized model file using one of the following approaches: > [tab] Using client.models.download() > > ```py theme={null} > client.models.download('OpenHermes-2.5-Mistral-7B/Q4_K_M') > ``` > > > [!NOTE] > > > > `client.models.download()` accepts either a string reference (`'model/quantization'`) or a `QuantizedFile` object. > > > > *** > > > > If the model has already been downloaded, the function exits immediately. Otherwise, a progress bar displays. > [tab] Using Model.download() > > ```py theme={null} > model = client.models.get('OpenHermes-2.5-Mistral-7B') > model.download('Q4_K_M') > ``` > [tab] Using QuantizedFile.download() > > ```py theme={null} > model = client.models.get('OpenHermes-2.5-Mistral-7B') > quantization = model.get_quantization('Q4_K_M') > quantization.download() > ``` ## Example usage ```py theme={null} from anaconda_ai import AnacondaAIClient client = AnacondaAIClient() # List all models models = client.models.list() for model in models: print(f"{model.name}: {model.num_parameters / 1e9:.1f}B parameters") # Get specific model details model = client.models.get('OpenHermes-2.5-Mistral-7B') print(f"Description: {model.description}") print(f"Trained for: {model.trained_for}") # Check available quantizations for quant in model.quantized_files: status = "downloaded" if quant.is_downloaded else "available" print(f" {quant.quant_method}: {status} ({quant.size_bytes / 1e9:.1f}GB)") # Download and use a quantization if not model.get_quantization('Q4_K_M').is_downloaded: model.download('Q4_K_M') quantization = model.get_quantization('Q4_K_M') print(f"Local path: {quantization.local_path}") ```