---
title: Florence-2-base-ft-3bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/Florence-2-base-ft-3bit"
md_url: "https://www.modelscope.cn/models/mlx-community/Florence-2-base-ft-3bit.md"
repository: mlx-community/Florence-2-base-ft-3bit
last_updated: 2024-12-20
license: mit
pipeline_tag: image-text-to-text
tasks:
  - image-text-to-text
model_type:
  - florence2
architectures:
  - Florence2ForConditionalGeneration
parameters: 40.6M
tensor_type:
  - F16
  - U32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
inference_backends:
  - "deploy_task vlm/text/emb"
  - "vllm 0.9.2"
downloads: 913
stars: 0
tags:
  - vision
  - mlx
---

# Florence-2-base-ft-3bit

> Florence-2-base-ft-3bit - mlx-community 在 ModelScope 开源的模型。mlx-community/Florence-2-base-ft-3bit This model was converted to MLX format from prince-canuma/Florence-2-base-ft using mlx-vlm version 0.1.0. Refer to the original model card for more details on…

mlx-community/Florence-2-base-ft-3bit 是 ModelScope 魔搭社区上的 40.6M 参数image-text-to-text模型，采用 mit 许可，可用 deploy_task vlm/text/emb、vllm 0.9.2 部署。

- **Repository**: mlx-community/Florence-2-base-ft-3bit
- **License**: mit
- **Tasks**: image-text-to-text
- **Parameters**: 40.6M
- **Inference backends**: deploy_task vlm/text/emb, vllm 0.9.2
- **Tags**: vision, mlx
- **Downloads**: 913
- **Stars**: 0
- **Last updated**: 2024-12-20

Source: https://www.modelscope.cn/models/mlx-community/Florence-2-base-ft-3bit

---

# mlx-community/Florence-2-base-ft-3bit
This model was converted to MLX format from [`prince-canuma/Florence-2-base-ft`]() using mlx-vlm version **0.1.0**.
Refer to the [original model card](https://huggingface.co/prince-canuma/Florence-2-base-ft) for more details on the model.
## Use with mlx

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

```bash
python -m mlx_vlm.generate --model mlx-community/Florence-2-base-ft-3bit --max-tokens 100 --temp 0.0
```