aisingapore/ Gemma-SEA-LION-v4-4B-VL:q6_k

5 yesterday

Gemma-SEA-LION-v4-4B-VL is a multilingual, multimodal model which has been pretrained and instruct-tuned for the Southeast Asia region. Developed by AI Singapore and funded by National Research Foundation, Singapore.

vision tools 
ollama run aisingapore/Gemma-SEA-LION-v4-4B-VL:q6_k

Details

yesterday

5f2ad42ade4f · 4.0GB ·

model
gemma3
·
3.88B
·
Q6_K
projector
clip
·
420M
·
F16
template
{{- $lastUserIdx := -1 -}} {{- range $idx, $msg := .Messages -}} {{- if eq $msg.Role "user" }}{{ $la
params
{ "stop": [ "<eos>", "<end_of_turn>" ] }

Readme

Gemma-SEA-LION-v4-4B-VL

[Last update: 2026-02-05]

SEA-LION is a collection of Large Language Models (LLMs) which have been pretrained and instruct-tuned for the Southeast Asia (SEA) region.

Gemma-SEA-LION-v4-4B-VL is a 4-billion parameter Vision-Language Model (VLM) built upon the gemma-3-4b-it architecture. To ensure domain adaptation for the region, the model underwent rigorous post-training on a curated dataset of approximately 6.7 million instruction-text pairs.

This extensive post-training instills multilingual and multicultural fluency, covering key SEA languages such as Indonesian, Vietnamese, Thai, Filipino, Tamil, Burmese, Malay. This curated dataset also includes a filtered open sourced set of tool-calling instruction-text pairs to impart these capabilities, in addition to linguistic fluency.

Gemma-SEA-LION-v4-4B-VL inherits the image and text capabilities from gemma-3-4b-it alongside its large context length of 128K tokens. Additionally, beyond extending the multilingual capabilities of the original gemma model for SEA languages, we experimented with:

  1. Adding function calling to the model to allow for this model to be used in tool calling applications.
  2. The visual parsing capabilities in Thai, Chinese and English.

SEA-LION stands for Southeast Asian Languages In One Network.

We performed Post-Training in English and SEA languages on gemma-3-4b-it, a decoder model using the gemma-3 architecture, to create Gemma-SEA-LION-v4-4B-VL.

For tokenization, the model employs the default tokenizer used in gemma-3-4b-it.

  • Developed by: AI Products Pillar, AI Singapore
  • Funded by: Singapore NRF
  • Shared by: AI Products Pillar, AI Singapore
  • Model type: Decoder
  • Context length: 128k
  • Language(s): Indonesian, Vietnamese, Thai, Filipino, Tamil, Burmese, Malay
  • License: Gemma
  • Finetuned from model: gemma-3-4b-it

For more details, please refer to AI Singapore’s HuggingFace page for this model. The original GGUF files can be obtained from this HuggingFace repository.