---
title: nanoVLM-460M
canonical_url: "https://www.modelscope.cn/models/AI-ModelScope/nanoVLM-460M"
md_url: "https://www.modelscope.cn/models/AI-ModelScope/nanoVLM-460M.md"
repository: AI-ModelScope/nanoVLM-460M
last_updated: 2025-09-01
license: mit
pipeline_tag: image-text-to-text
tasks:
  - image-text-to-text
parameters: 460.1M
tensor_type:
  - F32
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 23
stars: 0
tags:
  - vision-language
  - multimodal
  - research
---

# nanoVLM-460M

> nanoVLM-460M - AI-ModelScope 在 ModelScope 开源的模型。nanoVLM is a minimal and lightweight Vision-Language Model (VLM) designed for efficient training and experimentation. Built using pure PyTorch, the entire model architecture and training logic fits within 750…

AI-ModelScope/nanoVLM-460M 是 ModelScope 魔搭社区上的 460.1M 参数image-text-to-text模型，采用 mit 许可。

- **Repository**: AI-ModelScope/nanoVLM-460M
- **License**: mit
- **Tasks**: image-text-to-text
- **Parameters**: 460.1M
- **Tags**: vision-language, multimodal, research
- **Downloads**: 23
- **Stars**: 0
- **Last updated**: 2025-09-01

Source: https://www.modelscope.cn/models/AI-ModelScope/nanoVLM-460M

---

**nanoVLM** is a minimal and lightweight Vision-Language Model (VLM) designed for efficient training and experimentation. Built using pure PyTorch, the entire model architecture and training logic fits within ~750 lines of code. It combines a ViT-based image encoder (SigLIP-B/16-224-85M) with a lightweight causal language model (SmolLM2-135M), resulting in a compact 222M parameter model.

For more information, check out the base model on https://huggingface.co/lusxvr/nanoVLM-222M.

**Usage:**

Clone the nanoVLM repository: https://github.com/huggingface/nanoVLM.
Follow the install instructions and run the following code:

```python
from models.vision_language_model import VisionLanguageModel

model = VisionLanguageModel.from_pretrained("lusxvr/nanoVLM-460M")
```