Qwen-SEA-LION-v4-4B-VL
Qwen-SEA-LION-v4-4B-VL adapts Qwen3-VL-4B-Instruct with about nine million regional instruction-text pairs. It combines image and text inputs with text output. The release retains its parent's vision-language and tool-use functions.
How this release works
The card lists English, Burmese, Indonesian, Filipino, Malay, Tamil, Thai and Vietnamese. Its serving example uses the Qwen3-VL processor and conditional-generation model. The regional training stage focuses on instruction-text examples, so this is an adaptation of an existing vision model.Qwen-SEA-LION-v4-4B-VL official model card
How to assess it for your work
Practical guidance. Use the 4B release when you need an initial comparison for a small vision deployment. Include questions where the answer must come from the image, not from general knowledge. Compare incorrect field values and missed details with the 8B release before deciding whether the larger model adds enough value.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Access | Downloadable |
| Model identifiers | aisingapore/Qwen-SEA-LION-v4-4B-VL |
| Model size | 4 billion parametersQwen-SEA-LION-v4-4B-VL official model card |
| Context stated by the card | 256K tokensQwen-SEA-LION-v4-4B-VL official model card |
| License declared by the model card | MITQwen-SEA-LION-v4-4B-VL official model card |
| Base model | Qwen/Qwen3-VL-4B-InstructQwen-SEA-LION-v4-4B-VL official model card |
Related models
- Gemma-SEA-LION-v4-4B-VL
AI Singapore · SEA-LION v4
A 4B Gemma 3 vision-language model adapted for regional image understanding, visual parsing and tool calls.
Launch date not confirmedDownloadable - Qwen-SEA-LION-v4-8B-VL
AI Singapore · SEA-LION v4
An 8B Qwen3-VL model adapted with about nine million regional instruction-text pairs.
Launch date not confirmedDownloadable