---
title: NuExtract3-mlx-5bits
canonical_url: "https://www.modelscope.cn/models/numind/NuExtract3-mlx-5bits"
md_url: "https://www.modelscope.cn/models/numind/NuExtract3-mlx-5bits.md"
repository: numind/NuExtract3-mlx-5bits
last_updated: 2026-05-19
model_type:
  - qwen3_5
architectures:
  - Qwen3_5ForConditionalGeneration
base_model:
  - numind/NuExtract3
base_model_relation: quantized
parameters: 1.1B
tensor_type:
  - BF16
  - U32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 15
stars: 0
tags:
  - mlx
  - mlx-vlm
  - quantized
---

# NuExtract3-mlx-5bits

> NuExtract3-mlx-5bits - numind 在 ModelScope 开源的模型。numind/NuExtract3-mlx-5bits

numind/NuExtract3-mlx-5bits 是 ModelScope 魔搭社区上的 1.1B 参数机器学习模型，基于 numind/NuExtract3 构建。

- **Repository**: numind/NuExtract3-mlx-5bits
- **Parameters**: 1.1B
- **Base model**: numind/NuExtract3
- **Tags**: mlx, mlx-vlm, quantized
- **Downloads**: 15
- **Stars**: 0
- **Last updated**: 2026-05-19

Source: https://www.modelscope.cn/models/numind/NuExtract3-mlx-5bits

---

# numind/NuExtract3-mlx-5bits

MLX quantized version of `numind/NuExtract3`.

## Quantization

- mode: `affine`
- group_size: `64`
- bits: `5`
- dtype: `source/default`
- quant_predicate: `none`

## Usage

```bash
pip install -U mlx-vlm
mlx_vlm.generate --model numind/NuExtract3-mlx-5bits --prompt "your prompt"
```