data needs about 50.5 GB of memory at its main file (a 17.8 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 3 quants, from 14.9 GB to 18.0 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 128.8 GB.
25.2B Gemini‑4 model in GGUF format
The Data model is a 25.2 billion parameter Gemini‑4 architecture. It was trained on 262,144 context tokens and is released under the Apache‑2.0 license. The model is available in three GGUF files with unknown quantization.
Good at
- Large‑context text generation
- High‑parameter density
- Gemini‑4 architecture
Limits
- No vision support
- Large VRAM requirement
- Unknown quantization
Best for
- Research on large‑context LLMs
- Benchmarking Gemini‑4 models
- Developing custom applications
Who it’s for. Researchers and developers needing a high‑parameter Gemini‑4 model for text‑only tasks. The model is suitable for environments that can accommodate its memory footprint.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 14.9 GB | 47.6 GB | Too big | Get file → | |
| — | 17.8 GB | 50.5 GB | Too big | Get file → | |
| — | 18.0 GB | 50.8 GB | Too big | Get file → |
All available GGUF files use an unknown quantization. The 14.89 GB file requires about 47.6 GB of VRAM at 8 k context. The 17.79 GB file needs about 50.5 GB, and the 18.04 GB file needs about 50.8 GB. Choose the smallest file for tighter memory budgets.
What GPU do you need for data?
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: no quant fits at an 8K context.
- 32 GB VRAM: no quant fits at an 8K context.
- 48 GB VRAM: the best quant that fits is the main file (14.9 GB file, about 47.6 GB in use).
Which data quant should you choose?
If memory is tight, the smallest file is the first one in the table at 14.9 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about data
How much VRAM does data need?
About 50.5 GB at its main file with an 8K context window. That is the 17.8 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 data on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 47.6 GB, so you would need a larger GPU or CPU offloading.
What is the file size of data GGUF?
It depends on the quant: file is 14.9 GB, file is 17.8 GB, file is 18.0 GB.
What context length does data support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 32.2 GB at 8K and 128.8 GB at 32K.
Where can I download data GGUF?
The files are on Hugging Face in the ddh0/data repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does data use?
Hugging Face lists the license as apache-2.0. 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 this model on 8 GB VRAM?
No. The smallest GGUF file requires approximately 47.6 GB of VRAM at 8 k context.
What quantization is used?
All GGUF files are marked as unknown quantization.
Is this model vision‑capable?
No, the model has no vision support.