---
title: Idefics3-8B-Llama3-bf16
canonical_url: "https://www.modelscope.cn/models/mlx-community/Idefics3-8B-Llama3-bf16"
md_url: "https://www.modelscope.cn/models/mlx-community/Idefics3-8B-Llama3-bf16.md"
repository: mlx-community/Idefics3-8B-Llama3-bf16
last_updated: 2025-02-01
license: apache-2.0
model_type:
  - idefics3
architectures:
  - Idefics3ForConditionalGeneration
parameters: 8.5B
tensor_type:
  - BF16
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
inference_backends:
  - "deploy_task vlm/text/emb"
  - "vllm 0.9.2"
downloads: 994
stars: 0
tags:
  - multimodal
  - vision
  - image-text-to-text
  - mlx
---

# Idefics3-8B-Llama3-bf16

> Idefics3-8B-Llama3-bf16 - mlx-community 在 ModelScope 开源的模型。mlx-community/Idefics3-8B-Llama3-bf16 This model was converted to MLX format from HuggingFaceM4/Idefics3-8B-Llama3 using mlx-vlm version 0.1.12. Refer to the original model card for more details on…

mlx-community/Idefics3-8B-Llama3-bf16 是 ModelScope 魔搭社区上的 8.5B 参数机器学习模型，采用 apache-2.0 许可，可用 deploy_task vlm/text/emb、vllm 0.9.2 部署。

- **Repository**: mlx-community/Idefics3-8B-Llama3-bf16
- **License**: apache-2.0
- **Parameters**: 8.5B
- **Inference backends**: deploy_task vlm/text/emb, vllm 0.9.2
- **Tags**: multimodal, vision, image-text-to-text, mlx
- **Downloads**: 994
- **Stars**: 0
- **Last updated**: 2025-02-01

Source: https://www.modelscope.cn/models/mlx-community/Idefics3-8B-Llama3-bf16

---

# mlx-community/Idefics3-8B-Llama3-bf16
This model was converted to MLX format from [`HuggingFaceM4/Idefics3-8B-Llama3`]() using mlx-vlm version **0.1.12**.
Refer to the [original model card](https://huggingface.co/HuggingFaceM4/Idefics3-8B-Llama3) for more details on the model.
## Use with mlx

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

```bash
python -m mlx_vlm.generate --model mlx-community/Idefics3-8B-Llama3-bf16 --max-tokens 100 --temp 0.0 --prompt "Describe this image." --image <path_to_image>
```