---
title: LFM2.5-VL-450M-6bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/LFM2.5-VL-450M-6bit"
md_url: "https://www.modelscope.cn/models/mlx-community/LFM2.5-VL-450M-6bit.md"
repository: mlx-community/LFM2.5-VL-450M-6bit
last_updated: 2026-08-13
license: other
pipeline_tag: image-text-to-text
tasks:
  - image-text-to-text
model_type:
  - lfm2_vl
architectures:
  - Lfm2VlForConditionalGeneration
base_model:
  - LiquidAI/LFM2.5-VL-450M
base_model_relation: quantized
parameters: 165.3M
tensor_type:
  - BF16
  - U32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
  - ja
  - ko
  - fr
  - es
  - de
  - ar
  - zh
  - pt
downloads: 9
stars: 0
tags:
  - liquid
  - lfm2
  - lfm2-vl
  - edge
  - lfm2.5-vl
  - lfm2.5
  - mlx
---

# LFM2.5-VL-450M-6bit

> LFM2.5-VL-450M-6bit - mlx-community 在 ModelScope 开源的模型。mlx-community/LFM2.5-VL-450M-6bit This model was converted to MLX format from LiquidAI/LFM2.5-VL-450M using mlx-vlm version 0.4.4. Refer to the original model card for more details on the model. Use with…

mlx-community/LFM2.5-VL-450M-6bit 是 ModelScope 魔搭社区上的 165.3M 参数image-text-to-text模型，采用 other 许可，基于 LiquidAI/LFM2.5-VL-450M 构建。

- **Repository**: mlx-community/LFM2.5-VL-450M-6bit
- **License**: other
- **Tasks**: image-text-to-text
- **Parameters**: 165.3M
- **Base model**: LiquidAI/LFM2.5-VL-450M
- **Tags**: liquid, lfm2, lfm2-vl, edge, lfm2.5-vl, lfm2.5, mlx
- **Downloads**: 9
- **Stars**: 0
- **Last updated**: 2026-08-13

Source: https://www.modelscope.cn/models/mlx-community/LFM2.5-VL-450M-6bit

---

# mlx-community/LFM2.5-VL-450M-6bit
This model was converted to MLX format from [`LiquidAI/LFM2.5-VL-450M`]() using mlx-vlm version **0.4.4**.
Refer to the [original model card](https://huggingface.co/LiquidAI/LFM2.5-VL-450M) for more details on the model.
## Use with mlx

```bash
pip install -U mlx-vlm
```

```bash
python -m mlx_vlm.generate --model mlx-community/LFM2.5-VL-1.6B-4bit --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>
```