---
title: Llama-4-Scout-17B-16E-8bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/Llama-4-Scout-17B-16E-8bit"
md_url: "https://www.modelscope.cn/models/mlx-community/Llama-4-Scout-17B-16E-8bit.md"
repository: mlx-community/Llama-4-Scout-17B-16E-8bit
last_updated: 2025-04-06
license: other
model_type:
  - llama4
architectures:
  - Llama4ForConditionalGeneration
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - ar
  - de
  - en
  - es
  - fr
  - hi
  - id
  - it
  - pt
  - th
  - tl
  - vi
inference_backends:
  - "deploy_task vlm/text/emb"
  - "lmdeploy 0.9.1"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 431
stars: 0
tags:
  - facebook
  - meta
  - pytorch
  - llama
  - llama-4
  - mlx
---

# Llama-4-Scout-17B-16E-8bit

> Llama-4-Scout-17B-16E-8bit - mlx-community 在 ModelScope 开源的模型。mlx-community/Llama-4-Scout-17B-16E-8bit This model was converted to MLX format from meta-llama/Llama-4-Scout-17B-16E using mlx-vlm version 0.1.21. Refer to the original model card for more…

mlx-community/Llama-4-Scout-17B-16E-8bit 是 ModelScope 魔搭社区上的机器学习模型，采用 other 许可，可用 deploy_task vlm/text/emb、lmdeploy 0.9.1、sglang 0.5.2 部署。

- **Repository**: mlx-community/Llama-4-Scout-17B-16E-8bit
- **License**: other
- **Inference backends**: deploy_task vlm/text/emb, lmdeploy 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Tags**: facebook, meta, pytorch, llama, llama-4, mlx
- **Downloads**: 431
- **Stars**: 0
- **Last updated**: 2025-04-06

Source: https://www.modelscope.cn/models/mlx-community/Llama-4-Scout-17B-16E-8bit

---

# mlx-community/Llama-4-Scout-17B-16E-8bit
This model was converted to MLX format from [`meta-llama/Llama-4-Scout-17B-16E`]() using mlx-vlm version **0.1.21**.
Refer to the [original model card](https://huggingface.co/meta-llama/Llama-4-Scout-17B-16E) for more details on the model.
## Use with mlx

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

```bash
python -m mlx_vlm.generate --model mlx-community/Llama-4-Scout-17B-16E-8bit --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>
```