---
title: FastVLM-0.5B-bf16
canonical_url: "https://www.modelscope.cn/models/mlx-community/FastVLM-0.5B-bf16"
md_url: "https://www.modelscope.cn/models/mlx-community/FastVLM-0.5B-bf16.md"
repository: mlx-community/FastVLM-0.5B-bf16
last_updated: 2025-10-19
license: apple-amlr
pipeline_tag: image-text-to-text
tasks:
  - image-text-to-text
model_type:
  - llava_qwen2
architectures:
  - LlavaQwen2ForCausalLM
parameters: 622.7M
tensor_type:
  - BF16
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 675
stars: 0
tags:
  - mlx
---

# FastVLM-0.5B-bf16

> FastVLM-0.5B-bf16 - mlx-community 在 ModelScope 开源的模型。mlx-community/FastVLM-0.5B-bf16 This model was converted to MLX format from apple/FastVLM-0.5B using mlx-vlm from this PR. Refer to the original model card for more details on the model. Use with mlx

mlx-community/FastVLM-0.5B-bf16 是 ModelScope 魔搭社区上的 622.7M 参数image-text-to-text模型，采用 apple-amlr 许可。

- **Repository**: mlx-community/FastVLM-0.5B-bf16
- **License**: apple-amlr
- **Tasks**: image-text-to-text
- **Parameters**: 622.7M
- **Tags**: mlx
- **Downloads**: 675
- **Stars**: 0
- **Last updated**: 2025-10-19

Source: https://www.modelscope.cn/models/mlx-community/FastVLM-0.5B-bf16

---

# mlx-community/FastVLM-0.5B-bf16
This model was converted to MLX format from [`apple/FastVLM-0.5B`](https://huggingface.co/apple/FastVLM-0.5B) using mlx-vlm from [this PR](https://github.com/Blaizzy/mlx-vlm/pull/502).
Refer to the [original model card](https://huggingface.co/apple/FastVLM-0.5B) for more details on the model.
## Use with mlx

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

```bash
python -m mlx_vlm.generate --model mlx-community/FastVLM-0.5B-bf16 --max-tokens 100 --temperature 0.0 --prompt "Describe this image in detail." --image https://huggingface.co/datasets/huggingface/documentation-images/resolve/0052a70beed5bf71b92610a43a52df6d286cd5f3/diffusers/rabbit.jpg
```