Gemma SEA LION v4 27B IT needs about 21.2 GB of memory at Q4_K_M (a 16.5 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 3 quants, from 16.5 GB (Q4_K_M) to 54.0 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 16.6 GB.
Gemma SEA LION v4 27B IT – 27B parameter LLM with 128K context and vision
Gemma SEA LION v4 27B IT is a 27B parameter decoder model based on Gemma 3. It supports 128k token context and image‑text understanding. The model is finetuned on Southeast Asian languages and English.
Good at
- Southeast Asian language tasks
- Vision‑text reasoning
- Structured function calling
Limits
- No vision support on older quant files
- Large VRAM requirement for full precision
- License: Gemma Terms of Use
Best for
- Multilingual chatbots for SEA regions
- Document comprehension with images
- API integration with function calling
Who it’s for. Developers building multilingual applications for Southeast Asia. Researchers needing a large context LLM with vision capabilities.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 16.5 GB | 21.2 GB | Too big | Get file → | |
| Q8_0 | 28.7 GB | 33.4 GB | Too big | Get file → | |
| BF16 | 54.0 GB (3 parts) | 58.7 GB | Too big | Get file → |
For 16GB VRAM use Q4_K_M (file size 16.55 GB, ~21.2 GB memory at 8k context). For 32GB VRAM use Q8_0 (28.71 GB, ~33.4 GB). For maximum precision use BF16 shards (54.03 GB total, ~58.7 GB).
What GPU do you need for Gemma SEA LION v4 27B IT?
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: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: the best quant that fits is Q4_K_M (16.5 GB file, about 21.2 GB in use).
- 32 GB VRAM: the best quant that fits is Q4_K_M (16.5 GB file, about 21.2 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (28.7 GB file, about 33.4 GB in use).
Which Gemma SEA LION v4 27B IT quant should you choose?
Q4_K_M is the usual starting point for Gemma SEA LION v4 27B IT: it balances file size and quality well. Here it is a 16.5 GB file.
The Q8_0 file is 28.7 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 27B IT
How much VRAM does Gemma SEA LION v4 27B IT need?
About 21.2 GB at Q4_K_M with an 8K context window. That is the 16.5 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 27B IT on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 21.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Gemma SEA LION v4 27B IT GGUF?
It depends on the quant: Q4_K_M is 16.5 GB, Q8_0 is 28.7 GB, BF16 is 54.0 GB.
What context length does Gemma SEA LION v4 27B IT support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 4.2 GB at 8K and 16.6 GB at 32K.
Where can I download Gemma SEA LION v4 27B IT GGUF?
The files are on Hugging Face in the aisingapore/Gemma-SEA-LION-v4-27B-IT-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 27B IT 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 27B IT on 8GB VRAM?
No, the smallest quant requires ~21.2 GB memory at 8k context. 8GB VRAM is insufficient.
Does the model support image input?
Yes, it has image and text understanding capabilities, including visual Q&A and image‑grounded reasoning.
What is the context length?
The model supports 128k tokens of context.