# SEA-LION v4

SEA-LION version 4, released in August 2025, represents our first collection of multimodal models trained on Southeast Asian text. Each model offers unique strengths tailored to specific needs:

## Vision Language Models (VLMs)

* [**Gemma-SEA-LION-v4-4B-VL**](https://docs.sea-lion.ai/models/sea-lion-v4/gemma-sea-lion-v4-4b-vl) A lightweight model optimized for mobile and edge devices, bringing robust SEA language understanding to environments with strict memory and latency constraints.
* [**Gemma-SEA-LION-v4-27B-VL**](https://docs.sea-lion.ai/models/sea-lion-v4/gemma-sea-lion-v4-27b-vl) Our powerful vision-language model, expertly trained to interpret both images and text with a deep, nuanced understanding of Southeast Asian cultural contexts.
* [**Qwen-SEA-LION-v4-4B-VL and 8B-VL**](https://docs.sea-lion.ai/models/sea-lion-v4/qwen-sea-lion-v4-vl) Our latest specialized vision-language models, featuring a native 256K context window and superior OCR capabilities for Indonesian, Thai, and Vietnamese. The **4B model** is optimized for efficient edge deployment, while the **8B model** is engineered for complex multi-modal reasoning.

## Text Generation LLMs

* [**Apertus-SEA-LION-v4-8B**](https://docs.sea-lion.ai/models/sea-lion-v4/apertus-sea-lion-v4-8b) A versatile, compact model designed for high throughput and general-purpose SEA language tasks, offering an optimal trade-off between size and capability for developers.
* [**Gemma-SEA-LION-v4-27B**](https://docs.sea-lion.ai/models/sea-lion-v4/gemma-sea-lion-v4-27b) Suited for translation, abstractive summarisation, natural language inference, causal reasoning, metaphor understanding, question answering, paraphrasing, and sentiment analysis—applications where regional language support and advanced reasoning are critical.
* [**Gemma-SEA-LION-v4-27B-IT**](https://docs.sea-lion.ai/models/gemma-sea-lion-v4-27b#training-procedure) Suited for knowledge-intensive tasks and high-demand contexts where comprehensive language comprehension is essential.
  * *Available Variants:* [**Gemma-SEA-LION-v4-27B-IT-GGUF, NVFP4, FP8\_Dynamic**](https://docs.sea-lion.ai/models/gemma-sea-lion-v4-27b#gemma-sea-lion-v4-27b-it-quantized-version) support inference on a range of consumer-grade GPUs and are compatible with various inference engines.
* [**Qwen-SEA-LION-v4-32B-IT**](https://docs.sea-lion.ai/models/sea-lion-v4/qwen-sea-lion-v4-32b) Our flagship instruction-tuned model, designed for maximum performance in general SEA context tasks.
  * *Available Variants:* [**Qwen-SEA-LION-v4-32B-IT-4BIT / 8BIT**](https://docs.sea-lion.ai/models/qwen-sea-lion-v4-32b#available-versions)] offer a near-perfect balance of performance and efficiency, making the power of SEA-LION accessible on resource-constrained hardware like consumer-grade GPUs.

SEA-LION v4 continues our mission to create language models that understand and respond with greater cultural awareness and depth across Southeast Asia. In addition, SEA-LION v4 has the ability to handle both image and text input as a multimodal model.

For detailed information of each of the SEA-LION v4 models, please refer to their individual documentation pages via the links above.