smolvlm

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

SmolVLM - Local Image Analysis

SmolVLM - 本地图像分析

Analyze images locally using SmolVLM-2B, a state-of-the-art compact vision-language model optimized for Apple Silicon via mlx-vlm.

使用SmolVLM-2B在本地分析图像，这是一款通过mlx-vlm优化、适用于Apple Silicon的先进紧凑型视觉语言模型。

Quick Usage

快速使用

Describe an Image

描述图像

bash

python ~/.claude/skills/smolvlm/scripts/view_image.py /path/to/image.png

bash

python ~/.claude/skills/smolvlm/scripts/view_image.py /path/to/image.png

Ask a Question About an Image

询问图像相关问题

bash

python ~/.claude/skills/smolvlm/scripts/view_image.py /path/to/image.png "What text is visible?"

bash

python ~/.claude/skills/smolvlm/scripts/view_image.py /path/to/image.png "What text is visible?"

Specific Tasks

特定任务

bash

undefined

bash

undefined

Extract text (OCR)

提取文本（OCR）

python ~/.claude/skills/smolvlm/scripts/view_image.py screenshot.png "Extract all text"

UI analysis

UI分析

python ~/.claude/skills/smolvlm/scripts/view_image.py ui.png "Describe the UI elements"

Detailed description

详细描述

python ~/.claude/skills/smolvlm/scripts/view_image.py photo.jpg --detailed

undefined

python ~/.claude/skills/smolvlm/scripts/view_image.py photo.jpg --detailed

undefined

Effective Prompts

高效提示词

General Description

通用描述

```
"Describe this image"
```
- Basic description

"Describe this image in detail, including colors, composition, and any text"

- Comprehensive

```
"Describe this image"
```
- 基础描述

"Describe this image in detail, including colors, composition, and any text"

- 全面描述

Text Extraction (OCR)

文本提取（OCR）

"Extract all visible text from this image"

```
"What text appears in this screenshot?"
```
```
"Read the text in this document"
```

"Extract all visible text from this image"

```
"What text appears in this screenshot?"
```
```
"Read the text in this document"
```

UI/Screenshot Analysis

UI/截图分析

```
"Describe the user interface elements"
```

"What buttons and controls are visible?"

"Identify the application and its current state"

```
"Describe the user interface elements"
```

"What buttons and controls are visible?"

"Identify the application and its current state"

Visual Question Answering

视觉问答

```
"How many [objects] are in this image?"
```
```
"What color is the [object]?"
```
```
"Is there a [object] in this image?"
```

```
"How many [objects] are in this image?"
```
```
"What color is the [object]?"
```
```
"Is there a [object] in this image?"
```

Code/Technical

代码/技术类

```
"What programming language is shown?"
```
```
"Describe what this code does"
```

"Identify any errors in this code screenshot"

```
"What programming language is shown?"
```
```
"Describe what this code does"
```

"Identify any errors in this code screenshot"

Model Details

模型详情

Spec	Value
Model	SmolVLM-2B-Instruct
Size	~4GB
Peak Memory	5.8GB
Speed	~94 tok/s (M-series)
Supported Formats	PNG, JPG, JPEG, GIF, WebP

规格	数值
模型	SmolVLM-2B-Instruct
大小	~4GB
峰值内存	5.8GB
速度	~94 tok/s (M系列)
支持格式	PNG, JPG, JPEG, GIF, WebP

Requirements

要求

macOS with Apple Silicon (M1/M2/M3)
Python 3.10+
mlx-vlm package:
```
uv pip install mlx-vlm --system
```

搭载Apple Silicon的macOS（M1/M2/M3）
Python 3.10及以上版本
mlx-vlm包：
```
uv pip install mlx-vlm --system
```

Troubleshooting

故障排除

"Model not found": First run downloads the model (~4GB). Wait for completion.

Out of memory: Close other applications. Model needs ~6GB free RAM.

Slow first inference: Model loading takes 10-15s on first use, subsequent calls are faster.

"Model not found"：首次运行会下载模型（约4GB），请等待完成。

内存不足：关闭其他应用程序，模型需要约6GB可用内存。

首次推理速度慢：首次使用时模型加载需要10-15秒，后续调用会更快。