Gemma SEA LION v4 4B VL needs about 4.1 GB of memory at Q4_K_M (a 2.5 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 4 quants, from 2.5 GB (Q4_K_M) to 7.8 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.6 GB.
Gemma SEA LION v4 4B VL – a 4‑billion parameter vision‑language model for Southeast Asia
Gemma SEA LION v4 4B VL is a 4‑billion parameter VLM built on gemma‑3‑4b‑it. It supports 128k token context and has been post‑trained on 6.7 million instruction‑text pairs in SEA languages. The model includes vision, multilingual, and function‑calling capabilities.
Good at
- Vision‑language tasks in SEA languages
- Large context reasoning up to 128k tokens
- Tool‑calling via function calls
Limits
- No support for other modalities beyond vision and text
- Requires large VRAM for higher‑quality quantisations
- License is Gemma, not permissive for commercial use
Best for
- Multilingual chatbots for SEA markets
- Image‑captioning in local languages
- Tool‑integrated assistants
Who it’s for. Developers building applications that need vision and text understanding in Southeast Asian languages. Ideal for research and commercial use where the Gemma license permits.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 2.5 GB | 4.1 GB | Fits | Get file → | |
| Q6_K | 3.2 GB | 4.8 GB | Fits | Get file → | |
| Q8_0 | 4.1 GB | 5.8 GB | Fits | Get file → | |
| F16 | 7.8 GB | 9.4 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (2.49 GB, ~4.1 GB memory at 8k context). For 12 GB VRAM, Q6_K (3.19 GB, ~4.8 GB memory) is suitable. If more VRAM is available, Q8_0 or F16 offer higher precision.
What GPU do you need for Gemma SEA LION v4 4B VL?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: no quant fits at an 8K context.
- 6 GB VRAM: the best quant that fits is Q8_0 (4.1 GB file, about 5.8 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (4.1 GB file, about 5.8 GB in use).
- 12 GB VRAM: the best quant that fits is F16 (7.8 GB file, about 9.4 GB in use).
Which Gemma SEA LION v4 4B VL quant should you choose?
Q4_K_M is the usual starting point for Gemma SEA LION v4 4B VL: it balances file size and quality well. Here it is a 2.5 GB file.
The Q8_0 file is 4.1 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Gemma SEA LION v4 4B VL
How much VRAM does Gemma SEA LION v4 4B VL need?
About 4.1 GB at Q4_K_M with an 8K context window. That is the 2.5 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run Gemma SEA LION v4 4B VL on an 8 GB GPU?
Yes, with Q8_0: the 4.1 GB file needs about 5.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Gemma SEA LION v4 4B VL GGUF?
It depends on the quant: Q4_K_M is 2.5 GB, Q6_K is 3.2 GB, Q8_0 is 4.1 GB, F16 is 7.8 GB.
What context length does Gemma SEA LION v4 4B VL support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.6 GB at 32K.
Where can I download Gemma SEA LION v4 4B VL GGUF?
The files are on Hugging Face in the aisingapore/Gemma-SEA-LION-v4-4B-VL-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Gemma SEA LION v4 4B VL use?
Hugging Face lists the license as gemma. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run Gemma SEA LION v4 4B VL on 8 GB VRAM?
Yes, the Q4_K_M quantisation uses 2.49 GB file size and requires about 4.1 GB VRAM at 8k context, fitting within 8 GB.
Does the model support Chinese vision parsing?
The model supports visual parsing in Thai, Chinese and English, but Chinese parsing is limited to the visual domain.
Is the model licensed for commercial deployment?
The model uses the Gemma license, which may restrict commercial use; check the license terms before deployment.