> ## 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.

# anaconda ai download

export const GCell = ({children, className}) => <div className={`grid-table-cell ${className || ""}`} role="cell">
    {children}
  </div>;

export const GTH = ({children, className}) => <div className={`grid-table-th ${className || ""}`} role="columnheader">
    {children}
  </div>;

export const GRow = ({children}) => <div className="grid-table-row" role="row">{children}</div>;

export const GBody = ({children}) => <div className="grid-table-body" role="rowgroup">{children}</div>;

export const GHead = ({children}) => <div className="grid-table-head" role="rowgroup">{children}</div>;

export const GTable = ({children, className, cols}) => <div className={`grid-table not-prose overflow-hidden rounded-2xl ${className || ""}`} style={{
  "--grid-table-cols": cols
}} role="table">
    {children}
  </div>;

## Usage

```bash theme={null}
anaconda ai download <MODEL> [OPTIONS]
```

## Description

Downloads a quantized model file or safetensors collection from the backend. If the file is already downloaded, the command exits immediately unless `--force` is specified. A progress bar displays during the download.

## Download types

### Quantized models

A quantized model is a compressed GGUF file optimized for local inference. To download a quantized model, provide the model name and quantization type as `ModelName/QuantizationType`.

### Safetensors collections

<Note>
  Safetensors collection downloads require the `ai-catalyst` backend.

  ***

  You cannot launch a server or run inference on safetensors files directly from `anaconda ai`. Use a third-party framework to load and run the model after downloading.
</Note>

A safetensors collection contains all the files needed to run a model with a third-party inference framework, such as Hugging Face `transformers`. You can download a safetensors collection using the `--safetensors` flag.

A collection typically includes:

<GTable cols="40% 60%">
  <GHead>
    <GRow>
      <GTH>File</GTH>
      <GTH>Purpose</GTH>
    </GRow>
  </GHead>

  <GBody>
    <GRow>
      <GCell>`*.safetensors`</GCell>
      <GCell>Model weight files (may be sharded across multiple files for large models)</GCell>
    </GRow>

    <GRow>
      <GCell>`model.safetensors.index.json`</GCell>
      <GCell>Index file for sharded weight files</GCell>
    </GRow>

    <GRow>
      <GCell>`tokenizer.json`, `tokenizer_config.json`</GCell>
      <GCell>Tokenizer vocabulary, merge rules, and configuration</GCell>
    </GRow>

    <GRow>
      <GCell>`config.json`, `generation_config.json`</GCell>
      <GCell>Model architecture and default generation parameters</GCell>
    </GRow>

    <GRow>
      <GCell>`chat_template.jinja`</GCell>
      <GCell>Chat formatting template (if applicable)</GCell>
    </GRow>
  </GBody>
</GTable>

## Arguments

<GTable cols="25% 75%">
  <GHead>
    <GRow>
      <GTH>Argument</GTH>
      <GTH>Description</GTH>
    </GRow>
  </GHead>

  <GBody>
    <GRow>
      <GCell>`MODEL`</GCell>
      <GCell><Badge shape="pill" stroke color="blue">Required</Badge> Model identifier. Format depends on download type. <ul><li>Quantized model: `ModelName/QuantizationType`</li><li>Safetensors collection: `ModelName` only</li></ul></GCell>
    </GRow>
  </GBody>
</GTable>

## Options

<GTable cols="25% 25% 50%">
  <GHead>
    <GRow>
      <GTH>Option</GTH>
      <GTH>Default</GTH>
      <GTH>Description</GTH>
    </GRow>
  </GHead>

  <GBody>
    <GRow>
      <GCell>`--safetensors`</GCell>
      <GCell>`false`</GCell>
      <GCell>Download the safetensors collection for a model. Requires the `ai-catalyst` backend.</GCell>
    </GRow>

    <GRow>
      <GCell>`--force`</GCell>
      <GCell>`false`</GCell>
      <GCell>Force re-download if the model is already downloaded</GCell>
    </GRow>

    <GRow>
      <GCell>`--output, -o <PATH>`</GCell>

      <GCell />

      <GCell>For quantized downloads: hard-link the model file to this path. For safetensors downloads: directory to download files into (created if it does not exist).</GCell>
    </GRow>

    <GRow>
      <GCell>`--backend <BACKEND>`</GCell>
      <GCell>config value</GCell>
      <GCell>Select the inference backend</GCell>
    </GRow>

    <GRow>
      <GCell>`--at <SITE>`</GCell>

      <GCell />

      <GCell>Target a specific site defined in your configuration</GCell>
    </GRow>

    <GRow>
      <GCell>`--json`</GCell>
      <GCell>`false`</GCell>
      <GCell>Print output as JSON</GCell>
    </GRow>

    <GRow>
      <GCell>`-h, --help`</GCell>

      <GCell />

      <GCell>Show help for this command</GCell>
    </GRow>
  </GBody>
</GTable>

## Examples

**Download a model**

```bash theme={null}
anaconda ai download OpenHermes-2.5-Mistral-7B/Q4_K_M
```

**Force re-download of an existing model**

```bash theme={null}
anaconda ai download OpenHermes-2.5-Mistral-7B/Q4_K_M --force
```

**Download and hard-link to a custom path**

```bash theme={null}
anaconda ai download OpenHermes-2.5-Mistral-7B/Q4_K_M -o ./models/openhermes.gguf
```

**Download a safetensors collection**

```bash theme={null}
anaconda ai download --safetensors Qwen3-4B-Thinking-2507
```

**Download a safetensors collection to a specific directory**

```bash theme={null}
anaconda ai download --safetensors Qwen3-4B-Thinking-2507 --output ./my-model
```