---
title: SmolVLM2-500M-Video-Instruct-mlx
canonical_url: "https://www.modelscope.cn/models/mlx-community/SmolVLM2-500M-Video-Instruct-mlx"
md_url: "https://www.modelscope.cn/models/mlx-community/SmolVLM2-500M-Video-Instruct-mlx.md"
repository: mlx-community/SmolVLM2-500M-Video-Instruct-mlx
last_updated: 2025-02-21
license: apache-2.0
model_type:
  - smolvlm
architectures:
  - SmolVLMForConditionalGeneration
base_model:
  - HuggingFaceTB/SmolLM2-360M-Instruct
  - HuggingFaceTB/SmolVLM2-500M-Video-Instruct
base_model_relation: finetune
parameters: 507.5M
tensor_type:
  - BF16
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
inference_backends:
  - "deploy_task vlm/text/emb"
  - "vllm 0.9.2"
downloads: 656
stars: 0
tags:
  - mlx
---

# SmolVLM2-500M-Video-Instruct-mlx

> SmolVLM2-500M-Video-Instruct-mlx - mlx-community 在 ModelScope 开源的模型。HuggingFaceTB/SmolVLM2-500M-Video-Instruct-mlx This model was converted to MLX format from HuggingFaceTB/SmolVLM2-500M-Video-Instruct using mlx-vlm version 0.1.13. Refer to the original…

mlx-community/SmolVLM2-500M-Video-Instruct-mlx 是 ModelScope 魔搭社区上的 507.5M 参数机器学习模型，采用 apache-2.0 许可，基于 HuggingFaceTB/SmolLM2-360M-Instruct、HuggingFaceTB/SmolVLM2-500M-Video-Instruct 构建，可用 deploy_task vlm/text/emb、vllm 0.9.2 部署。

- **Repository**: mlx-community/SmolVLM2-500M-Video-Instruct-mlx
- **License**: apache-2.0
- **Parameters**: 507.5M
- **Base model**: HuggingFaceTB/SmolLM2-360M-Instruct, HuggingFaceTB/SmolVLM2-500M-Video-Instruct
- **Inference backends**: deploy_task vlm/text/emb, vllm 0.9.2
- **Tags**: mlx
- **Downloads**: 656
- **Stars**: 0
- **Last updated**: 2025-02-21

Source: https://www.modelscope.cn/models/mlx-community/SmolVLM2-500M-Video-Instruct-mlx

---

# HuggingFaceTB/SmolVLM2-500M-Video-Instruct-mlx
This model was converted to MLX format from [`HuggingFaceTB/SmolVLM2-500M-Video-Instruct`]() using mlx-vlm version **0.1.13**.
Refer to the [original model card](https://huggingface.co/HuggingFaceTB/SmolVLM2-500M-Video-Instruct) for more details on the model.
## Use with mlx

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

```bash
python -m mlx_vlm.generate --model mlx-community/SmolVLM2-500M-Video-Instruct-mlx --image https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg --prompt "Can you describe this image?"
```