---
title: LocateAnything-3B-4bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/LocateAnything-3B-4bit"
md_url: "https://www.modelscope.cn/models/mlx-community/LocateAnything-3B-4bit.md"
repository: mlx-community/LocateAnything-3B-4bit
last_updated: 2026-05-30
license: other
pipeline_tag: image-text-to-text
tasks:
  - image-text-to-text
model_type:
  - locateanything
architectures:
  - LocateAnythingForConditionalGeneration
base_model:
  - nvidia/LocateAnything-3B
base_model_relation: quantized
parameters: 1.0B
tensor_type:
  - BF16
  - U32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
downloads: 216
stars: 1
tags:
  - mlx
  - vision
  - object-detection
  - grounding
  - locateanything
  - nvidia
  - eagle
---

# LocateAnything-3B-4bit

> LocateAnything-3B-4bit - mlx-community 在 ModelScope 开源的模型。mlx-community/LocateAnything-3B-4bit

mlx-community/LocateAnything-3B-4bit 是 ModelScope 魔搭社区上的 1.0B 参数image-text-to-text模型，采用 other 许可，基于 nvidia/LocateAnything-3B 构建。

- **Repository**: mlx-community/LocateAnything-3B-4bit
- **License**: other
- **Tasks**: image-text-to-text
- **Parameters**: 1.0B
- **Base model**: nvidia/LocateAnything-3B
- **Tags**: mlx, vision, object-detection, grounding, locateanything, nvidia, eagle
- **Downloads**: 216
- **Stars**: 1
- **Last updated**: 2026-05-30

Source: https://www.modelscope.cn/models/mlx-community/LocateAnything-3B-4bit

---

# 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.