---
title: numind-NuExtract-2.0-8B-MLX
canonical_url: "https://www.modelscope.cn/models/mlx-community/numind-NuExtract-2.0-8B-MLX"
md_url: "https://www.modelscope.cn/models/mlx-community/numind-NuExtract-2.0-8B-MLX.md"
repository: mlx-community/numind-NuExtract-2.0-8B-MLX
last_updated: 2026-04-14
license: mit
pipeline_tag: image-text-to-text
tasks:
  - image-text-to-text
model_type:
  - qwen2_5_vl
architectures:
  - Qwen2_5_VLForConditionalGeneration
base_model:
  - numind/NuExtract-2.0-8B
base_model_relation: finetune
parameters: 8.3B
tensor_type:
  - BF16
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
inference_backends:
  - "deploy_task vlm/text/emb"
  - "lmdeploy 0.9.1"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 9
stars: 0
tags:
  - mlx
  - mlx-vlm
  - qwen2_5_vl
  - multimodal
  - document-understanding
  - image-text-to-text
  - unquantized
---

# numind-NuExtract-2.0-8B-MLX

> numind-NuExtract-2.0-8B-MLX - mlx-community 在 ModelScope 开源的模型。numind-NuExtract-2.0-8B-MLX

mlx-community/numind-NuExtract-2.0-8B-MLX 是 ModelScope 魔搭社区上的 8.3B 参数image-text-to-text模型，采用 mit 许可，基于 numind/NuExtract-2.0-8B 构建，可用 deploy_task vlm/text/emb、lmdeploy 0.9.1、sglang 0.5.2 部署。

- **Repository**: mlx-community/numind-NuExtract-2.0-8B-MLX
- **License**: mit
- **Tasks**: image-text-to-text
- **Parameters**: 8.3B
- **Base model**: numind/NuExtract-2.0-8B
- **Inference backends**: deploy_task vlm/text/emb, lmdeploy 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Tags**: mlx, mlx-vlm, qwen2_5_vl, multimodal, document-understanding, image-text-to-text, unquantized
- **Downloads**: 9
- **Stars**: 0
- **Last updated**: 2026-04-14

Source: https://www.modelscope.cn/models/mlx-community/numind-NuExtract-2.0-8B-MLX

---

# numind-NuExtract-2.0-8B-MLX

This repository contains an unquantized MLX conversion of [numind/NuExtract-2.0-8B](https://huggingface.co/numind/NuExtract-2.0-8B) for Apple Silicon inference with [mlx-vlm](https://github.com/Blaizzy/mlx-vlm).

## Provenance

- Upstream model: `numind/NuExtract-2.0-8B`
- Upstream authors: NuMind
- Conversion type: direct MLX format conversion
- Quantization: none
- Conversion tool: `mlx-vlm 0.4.2`
- Weight format: `safetensors`
- Approximate repository size: 16.6 GB

## Disclaimer

- This is not a new fine-tune, retrain, or modified checkpoint.
- This repository exists only to make the original model usable through `mlx-vlm` on Apple Silicon.
- Model behavior, capabilities, limitations, benchmarks, and intended-use guidance come from the upstream model card.
- Credit for the original model, training, evaluation, and documentation belongs to NuMind.
- If you want the canonical model documentation, use the upstream repository: [numind/NuExtract-2.0-8B](https://huggingface.co/numind/NuExtract-2.0-8B).

## License

The upstream model card lists the model license as MIT. This MLX conversion is intended to be shared under the same upstream license and terms.

## Use with `mlx-vlm`

```python
import json

from PIL import Image
from mlx_vlm import generate, load

model, processor = load("mlx-community/numind-NuExtract-2.0-8B-MLX")

template = json.dumps(
	{
		"invoice_number": "verbatim-string",
		"total": "number",
	},
	indent=2,
)

messages = [{"role": "user", "content": [{"type": "image", "image": "embedded"}]}]
prompt = processor.tokenizer.apply_chat_template(
	messages,
	template=template,
	tokenize=False,
	add_generation_prompt=True,
)

image = Image.open("document.png").convert("RGB")
result = generate(
	model,
	processor,
	prompt=prompt,
	image=image,
	max_tokens=2048,
	temperature=0.0,
	verbose=False,
)

print(result.text)
```

NuExtract works best with temperature at or very close to `0.0` for extraction workloads.