Boogu Image Base GGUFs needs about 9.5 GB of memory at Q5_0 (a 8.0 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 5 quants, from 6.8 GB (Q4_0) to 11.6 GB (Q8_0).
Boogu Image Base GGUFs – 10.3B parameter multimodal model
Boogu Image Base GGUFs is a 10.3B parameter model in the Boogu family, built on the lumina2 architecture. It supports image generation and editing with a unified pipeline. The model is released under the Apache-2.0 license.
Good at
- Text‑to‑image generation
- Image editing
- Chinese‑English text rendering
Limits
- No vision support in the base GGUFs
- Requires specific VAE and text encoder
- No K‑quant options
Best for
- Local image generation on a single GPU
- Fine‑tuning for image editing tasks
- Research on multimodal generation
Who it’s for. Researchers and developers who need an open‑source multimodal model for image generation and editing. The model is suitable for those who can provide the required VAE and text encoder and are comfortable with a flat quantization approach.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_0 | 6.8 GB | 8.2 GB | Too big | Get file → | |
| Q4_1 | 7.4 GB | 8.8 GB | Too big | Get file → | |
| Q5_0 | 8.0 GB | 9.5 GB | Too big | Get file → | |
| Q5_1 | 8.6 GB | 10.2 GB | Too big | Get file → | |
| Q8_0 | 11.6 GB | 13.5 GB | Too big | Get file → |
For an 8 GB VRAM setup, Q4_0 (6.84 GB file, 8.2 GB memory at 8k context) is recommended. If more VRAM is available, Q4_1 (7.44 GB file, 8.8 GB memory) or Q5_0 (8.04 GB file, 9.5 GB memory) can be used. Q8_0 requires the most memory (13.5 GB).
What GPU do you need for Boogu Image Base GGUFs?
These figures add the file size, an fp16 KV cache at an 8K context window 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: the best quant that fits is Q5_1 (8.6 GB file, about 10.2 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (11.6 GB file, about 13.5 GB in use).
Which Boogu Image Base GGUFs quant should you choose?
Q5_0 (8.0 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.
If memory is tight, the smallest file is Q4_0 at 6.8 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Boogu Image Base GGUFs
How much VRAM does Boogu Image Base GGUFs need?
About 9.5 GB at Q5_0 with an 8K context window. That is the 8.0 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 Boogu Image Base GGUFs on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 8.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Boogu Image Base GGUFs GGUF?
It depends on the quant: Q4_0 is 6.8 GB, Q4_1 is 7.4 GB, Q5_0 is 8.0 GB, Q5_1 is 8.6 GB, Q8_0 is 11.6 GB.
Where can I download Boogu Image Base GGUFs GGUF?
The files are on Hugging Face in the realrebelai/Boogu-Image-Base_GGUFs repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Boogu Image Base GGUFs 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 Boogu Image Base on 8 GB VRAM?
Yes, the Q4_0 quantization uses 6.84 GB file size and requires approximately 8.2 GB VRAM at 8k context, which fits an 8 GB GPU.
Does the model support vision tasks?
The base GGUFs do not include vision support; they focus on image generation and editing.
What license applies to this model?
The model is released under the Apache-2.0 license.