---
title: nanoLLaVA-4bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/nanoLLaVA-4bit"
md_url: "https://www.modelscope.cn/models/mlx-community/nanoLLaVA-4bit.md"
repository: mlx-community/nanoLLaVA-4bit
last_updated: 2024-12-26
license: apache-2.0
model_type:
  - llava-qwen2
architectures:
  - BunnyQwenForCausalLM
parameters: 656.8M
tensor_type:
  - F16
  - U32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
downloads: 998
stars: 0
tags:
  - llava
  - multimodal
  - qwen
  - mlx
---

# nanoLLaVA-4bit

> nanoLLaVA-4bit - mlx-community 在 ModelScope 开源的模型。mlx-community/nanoLLaVA-4bit This model was converted to MLX format from qnguyen3/nanoLLaVA using mlx-vllm version 0.0.3. Refer to the original model card for more details on the model. Use with mlx

mlx-community/nanoLLaVA-4bit 是 ModelScope 魔搭社区上的 656.8M 参数机器学习模型，采用 apache-2.0 许可。

- **Repository**: mlx-community/nanoLLaVA-4bit
- **License**: apache-2.0
- **Parameters**: 656.8M
- **Tags**: llava, multimodal, qwen, mlx
- **Downloads**: 998
- **Stars**: 0
- **Last updated**: 2024-12-26

Source: https://www.modelscope.cn/models/mlx-community/nanoLLaVA-4bit

---

# mlx-community/nanoLLaVA-4bit
This model was converted to MLX format from [`qnguyen3/nanoLLaVA`]() using mlx-vllm version **0.0.3**.
Refer to the [original model card](https://huggingface.co/qnguyen3/nanoLLaVA) for more details on the model.
## Use with mlx

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

```bash
python -m mlx_vlm.generate --model mlx-community/nanoLLaVA-4bit --max-tokens 100 --temp 0.0
```