> ## Documentation Index
> Fetch the complete documentation index at: https://forge-64364c0e.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Convert

> Convert SafeTensors models to GGUF format with configurable output types

# Convert (05)

Convert SafeTensors models (HuggingFace format) to GGUF files compatible with llama.cpp, Ollama, LM Studio, and other GGUF-based runtimes.

<img src="https://mintcdn.com/forge-64364c0e/ndaDrHy7hzGW88bh/images/light/convert.png?fit=max&auto=format&n=ndaDrHy7hzGW88bh&q=85&s=18761a22bc286c0f835b5d0d2faa4050" alt="Convert Module" width="3440" height="1406" data-path="images/light/convert.png" />

<Note>
  Requires **Python 3.10+** and a one-time dependency setup (\~500 MB). The convert environment is separate from the training environment and can be managed in [Settings](/modules/settings).
</Note>

## First-Time Setup

<Steps>
  <Step title="Detect Python">
    ForgeAI checks for Python 3 on launch
  </Step>

  <Step title="Install dependencies">
    Click **INSTALL DEPENDENCIES** — creates a virtual environment with `transformers`, `torch`, `safetensors`, `sentencepiece`, `protobuf`
  </Step>

  <Step title="GPU detection">
    ForgeAI detects your GPU and installs the right PyTorch variant (CUDA for NVIDIA, CPU otherwise)
  </Step>
</Steps>

The hero panel shows status indicators: PYTHON, VENV, SCRIPT, PACKAGES.

## Output Types

| Type      | Description            | Use Case                            |
| --------- | ---------------------- | ----------------------------------- |
| **F16**   | 16-bit float (default) | Best balance of size and precision  |
| **BF16**  | Brain float 16         | Better precision for large models   |
| **F32**   | Full 32-bit float      | Maximum precision, largest file     |
| **Q8\_0** | 8-bit quantized        | Smaller output, slight quality loss |
| **AUTO**  | Detect from source     | Matches source precision            |

## Model Analysis

After selecting a source, ForgeAI shows:

| Field        | Description                                 |
| ------------ | ------------------------------------------- |
| ARCHITECTURE | Model architecture (e.g., LlamaForCausalLM) |
| HIDDEN SIZE  | Embedding dimension                         |
| LAYERS       | Number of transformer layers                |
| VOCAB SIZE   | Tokenizer vocabulary size                   |
| SAFETENSORS  | Number of weight files                      |

File checks verify: `config.json` (required), tokenizer files, safetensors weights.

## Workflow

<Steps>
  <Step title="Select source">
    Pick a SafeTensors repo from the list (downloaded via [Hub](/modules/hub)) or click **GO TO HUB**
  </Step>

  <Step title="Review analysis">
    Check architecture, file counts, and file checks
  </Step>

  <Step title="Choose output type">
    Select F16, BF16, F32, Q8\_0, or AUTO
  </Step>

  <Step title="Convert">
    Click **CONVERT TO GGUF**, choose output location, monitor progress
  </Step>

  <Step title="Result">
    See output path and size. Click **LOAD MODEL** to use immediately in ForgeAI.
  </Step>
</Steps>

<Tip>
  After conversion, you can quantize the GGUF output further using the [Compress](/modules/optimize) module to create smaller variants (Q4\_K\_M, Q5\_K\_M, etc.).
</Tip>