---
title: llava-phi-3-mini-8bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/llava-phi-3-mini-8bit"
md_url: "https://www.modelscope.cn/models/mlx-community/llava-phi-3-mini-8bit.md"
repository: mlx-community/llava-phi-3-mini-8bit
last_updated: 2024-12-19
license: apache-2.0
model_type:
  - llava
architectures:
  - LlavaForConditionalGeneration
parameters: 1.2B
tensor_type:
  - F16
  - U32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
inference_backends:
  - "deploy_task vlm/text/emb"
  - "lmdeploy 0.9.1"
  - "lmdeploy_turbomind 0.9.1"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 992
stars: 0
tags:
  - llava
  - multimodal
  - phi-mini-3
  - mlx
---

# llava-phi-3-mini-8bit

> llava-phi-3-mini-8bit - mlx-community 在 ModelScope 开源的模型。mlx-community/llava-phi-3-mini-8bit This model was converted to MLX format from qnguyen3/nanoLLaVAxtuner/llava-phi-3-mini-hf using mlx-vllm version 0.0.3. Refer to the original model card for more…

mlx-community/llava-phi-3-mini-8bit 是 ModelScope 魔搭社区上的 1.2B 参数机器学习模型，采用 apache-2.0 许可，可用 deploy_task vlm/text/emb、lmdeploy 0.9.1、lmdeploy_turbomind 0.9.1 部署。

- **Repository**: mlx-community/llava-phi-3-mini-8bit
- **License**: apache-2.0
- **Parameters**: 1.2B
- **Inference backends**: deploy_task vlm/text/emb, lmdeploy 0.9.1, lmdeploy_turbomind 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Tags**: llava, multimodal, phi-mini-3, mlx
- **Downloads**: 992
- **Stars**: 0
- **Last updated**: 2024-12-19

Source: https://www.modelscope.cn/models/mlx-community/llava-phi-3-mini-8bit

---

# mlx-community/llava-phi-3-mini-8bit
This model was converted to MLX format from [`qnguyen3/nanoLLaVAxtuner/llava-phi-3-mini-hf`]() using mlx-vllm version **0.0.3**.
Refer to the [original model card](xtuner/llava-phi-3-mini-hf) for more details on the model.
## Use with mlx

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

```bash
python -m mlx_vlm.generate --model mlx-community/llava-phi-3-mini-8bit \
--prompt "what are these?" --image "http://images.cocodataset.org/val2017/000000039769.jpg" \
--max-tokens 100 --temp 0.0 
```