---
title: Unlimited-OCR-bf16
canonical_url: "https://www.modelscope.cn/models/mlx-community/Unlimited-OCR-bf16"
md_url: "https://www.modelscope.cn/models/mlx-community/Unlimited-OCR-bf16.md"
repository: mlx-community/Unlimited-OCR-bf16
last_updated: 2026-08-01
license: mit
pipeline_tag: image-text-to-text
tasks:
  - image-text-to-text
model_type:
  - unlimited-ocr
architectures:
  - UnlimitedOCRForCausalLM
base_model:
  - baidu/Unlimited-OCR
base_model_relation: finetune
parameters: 3.3B
tensor_type:
  - BF16
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - multilingual
downloads: 53
stars: 0
tags:
  - baidu
  - vision-language
  - ocr
  - custom_code
  - mlx
  - mlx-vlm
  - bfloat16
---

# Unlimited-OCR-bf16

> Unlimited-OCR-bf16 - mlx-community 在 ModelScope 开源的模型。Unlimited-OCR — MLX bf16

mlx-community/Unlimited-OCR-bf16 是 ModelScope 魔搭社区上的 3.3B 参数image-text-to-text模型，采用 mit 许可，基于 baidu/Unlimited-OCR 构建。

- **Repository**: mlx-community/Unlimited-OCR-bf16
- **License**: mit
- **Tasks**: image-text-to-text
- **Parameters**: 3.3B
- **Base model**: baidu/Unlimited-OCR
- **Tags**: baidu, vision-language, ocr, custom_code, mlx, mlx-vlm, bfloat16
- **Downloads**: 53
- **Stars**: 0
- **Last updated**: 2026-08-01

Source: https://www.modelscope.cn/models/mlx-community/Unlimited-OCR-bf16

---

# Unlimited-OCR — MLX bf16

This repository contains the **unquantized bfloat16 MLX conversion** of Baidu's official [`baidu/Unlimited-OCR`](https://huggingface.co/baidu/Unlimited-OCR) checkpoint. It is published for Apple Silicon inference with [`mlx-vlm`](https://github.com/Blaizzy/mlx-vlm) and maintained for use by [`shuuul/aimd`](https://github.com/shuuul/aimd).

The model architecture, tokenizer, processor configuration, prompts, and MIT license come from the official checkpoint. Refer to the [official model card](https://huggingface.co/baidu/Unlimited-OCR) and [Unlimited-OCR repository](https://github.com/baidu/Unlimited-OCR) for model details, capabilities, limitations, and attribution.

## Conversion details

| Setting | Value |
|---|---|
| Source | `baidu/Unlimited-OCR` |
| Tool | `mlx-vlm 0.6.8` |
| MLX runtime used for conversion | `mlx 0.32.0` |
| Output precision | `bf16` |
| Quantization | `none` |
| Repository size | 6.22 GiB |

Weights are stored as bfloat16 without weight quantization.

Conversion command:

```bash
mlx_vlm.convert \
  --hf-path baidu/Unlimited-OCR \
  --mlx-path ./Unlimited-OCR-bf16 \
  --dtype bfloat16
```

## Use with AIMD

On macOS/Apple Silicon, install AIMD and run OCR directly:

```bash
uv tool install --force "aimd-tool @ git+https://github.com/shuuul/aimd.git@main"
aimd scan.pdf --task ocr --model unlimited_ocr_bf16
```

`unlimited_ocr` defaults to the 4-bit repository. AIMD runs each page in Unlimited-OCR's single-image gundam mode with prompt `document parsing.`, `cropping=True`, `base_size=1024`, `image_size=640`, and a sliding-window no-repeat n-gram guard. See the [AIMD README](https://github.com/shuuul/aimd#ocr-for-scanned-pdfs-and-images) for the complete runtime behavior.

## Use with mlx-vlm

```bash
pip install -U "mlx-vlm>=0.6.8"
python -m mlx_vlm.generate \
  --model mlx-community/Unlimited-OCR-bf16 \
  --image scan.png \
  --prompt "document parsing." \
  --max-tokens 8192 \
  --temperature 0
```

Unlimited-OCR support first shipped in `mlx-vlm 0.6.4`; `0.6.8` or newer is recommended to match the conversion environment.

## Available MLX weights

| Precision | Repository | Size |
|---|---|---:|
| 4bit | [`mlx-community/Unlimited-OCR-4bit`](https://huggingface.co/mlx-community/Unlimited-OCR-4bit) | 2.29 GiB |
| 6bit | [`mlx-community/Unlimited-OCR-6bit`](https://huggingface.co/mlx-community/Unlimited-OCR-6bit) | 2.98 GiB |
| 8bit | [`mlx-community/Unlimited-OCR-8bit`](https://huggingface.co/mlx-community/Unlimited-OCR-8bit) | 3.66 GiB |
| bf16 | [`mlx-community/Unlimited-OCR-bf16`](https://huggingface.co/mlx-community/Unlimited-OCR-bf16) | 6.22 GiB |

## License and attribution

The upstream checkpoint is released under the MIT license. This repository is a format conversion and does not modify the upstream model architecture or claim ownership of Baidu's model.