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

# Backends

> Choose between the ONNX and PyTorch embedding backends

## Backend comparison

| Backend          | Startup | PyTorch required | Custom HF models          |
| ---------------- | ------- | ---------------- | ------------------------- |
| `onnx` (default) | \~100ms | No               | ONNX-exported models only |
| `torch`          | \~2–3s  | Yes              | Any HuggingFace model     |

## ONNX backend (default)

Uses [fastembed](https://github.com/qdrant/fastembed) with ONNX Runtime. Recommended for most users.

* Fast startup (\~100ms model load on first `embed()` call)
* No PyTorch installation required
* Works with ONNX-exported HuggingFace models

```bash theme={null}
# Default — no configuration needed
vecgrep
```

## PyTorch backend

Uses [sentence-transformers](https://www.sbert.net/) with PyTorch. Use this when you need a model that isn't available in ONNX format.

* Slower startup (\~2–3s)
* Supports any HuggingFace sentence-transformer model
* Automatically uses Metal (Apple Silicon), CUDA (NVIDIA), or CPU

```bash theme={null}
VECGREP_BACKEND=torch vecgrep
```