---
license: other
license_name: nvidia-license
license_link: https://huggingface.co/nvidia/LocateAnything-3B/blob/main/LICENSE
language:
- en
base_model:
- nvidia/LocateAnything-3B
pipeline_tag: image-text-to-text
library_name: mlx-vlm
tags:
- mlx
- vision
- object-detection
- grounding
- locateanything
- nvidia
- eagle
---

# mlx-community/LocateAnything-3B-4bit

MLX mixed 4/8-bit (`mixed_4_8`, ~6.7 bits/weight) conversion of [`nvidia/LocateAnything-3B`](https://huggingface.co/nvidia/LocateAnything-3B),
a vision-language model for fast, high-quality visual grounding (object detection,
referring-expression grounding, pointing, GUI/text localization). Converted with
[`mlx-vlm`](https://github.com/Blaizzy/mlx-vlm) for Apple Silicon.

Box coordinates stay accurate (within ~1-2 quant levels of bf16); semantic labels may generalize (e.g. `object` instead of `remote`). Pure 4-bit was not released because quantizing the tied `embed_tokens`/`lm_head` destroys coordinate-token precision.

## Requirements

> **Note:** LocateAnything support in `mlx-vlm` currently lives in a pull request
> and is **not yet in a released `mlx-vlm`**. Until it merges, install from the
> branch that adds the `locateanything` model:
>
> ```bash
> pip install "git+https://github.com/beshkenadze/mlx-vlm@feat/locateanything-3b"
> ```

## Usage

```bash
python -m mlx_vlm.generate --model mlx-community/LocateAnything-3B-4bit \
  --image http://images.cocodataset.org/val2017/000000039769.jpg \
  --prompt "Detect all objects in the image." --max-tokens 128 --temperature 0.0
```

Output is structured coordinate tokens, e.g.
`<ref>remote</ref><box><64><152><273><244></box>` with coordinates quantized to
`<0>`..`<1000>` (normalized). Decoding modes: autoregressive (`slow`, default) and
**Parallel Box Decoding** (`fast`/`hybrid`, ~2x faster) via `generation_mode`.

## Attribution & license

- Derived from **nvidia/LocateAnything-3B** — released under the
  [NVIDIA License](https://huggingface.co/nvidia/LocateAnything-3B/blob/main/LICENSE):
  **non-commercial, research/academic use only** (commercial use not permitted
  except by NVIDIA). Redistribution must retain this license and attribution.
- Vision encoder: **MoonViT-SO-400M** (MIT). Language model: **Qwen2.5-3B-Instruct**
  (Qwen Research License). Part of the [Eagle VLM](https://github.com/NVlabs/EAGLE) family.

The `LICENSE` file from the source model is included in this repo.