Creative Quants needs about 30.3 GB of memory at its main file (a 16.9 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 5 quants, from 8.6 GB to 17.7 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 51.5 GB.
12‑billion‑parameter Gemma4 model for creative text generation
Creative Quants is a 12 billion‑parameter Gemma4 architecture model. It was trained on 262,144 context tokens. The model is available in multiple GGUF file sizes ranging from 8.58 GB to 17.65 GB.
Good at
- Creative writing and storytelling
- Generating imaginative prompts
- Producing varied text styles
Limits
- Large context length requires high VRAM
- No license information provided
- No vision or multimodal support
Best for
- Writing fiction drafts
- Brainstorming creative ideas
- Generating dialogue scripts
Who it’s for. Developers and writers who need a large language model for creative content. The model can be run locally with llama.cpp using the provided GGUF files.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 8.6 GB | 22.0 GB | Too big | Get file → | |
| — | 8.6 GB | 22.0 GB | Too big | Get file → | |
| — | 16.9 GB | 30.3 GB | Too big | Get file → | |
| — | 16.9 GB | 30.3 GB | Too big | Get file → | |
| — | 17.7 GB | 31.0 GB | Too big | Get file → |
For 8 GB VRAM, use the 8.58 GB GGUF file; memory estimate is about 22 GB at 8 k context. For 16 GB VRAM, the 16.87 GB file uses roughly 30.3 GB. For 24 GB VRAM, the 17.65 GB file needs about 31 GB. Estimates are approximate.
What GPU do you need for Creative Quants?
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 the main file (8.6 GB file, about 22.0 GB in use).
- 32 GB VRAM: the best quant that fits is the main file (17.7 GB file, about 31.0 GB in use).
Which Creative Quants quant should you choose?
If memory is tight, the smallest file is the first one in the table at 8.6 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 Creative Quants
How much VRAM does Creative Quants need?
About 30.3 GB at its main file with an 8K context window. That is the 16.9 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 Creative Quants on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 22.0 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Creative Quants GGUF?
It depends on the quant: file is 8.6 GB, file is 8.6 GB, file is 16.9 GB, file is 16.9 GB, file is 17.7 GB.
What context length does Creative Quants support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 12.9 GB at 8K and 51.5 GB at 32K.
Where can I download Creative Quants GGUF?
The files are on Hugging Face in the drakira/Creative-Quants repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
Can I run Creative Quants on 8 GB VRAM?
The 8.58 GB GGUF file requires about 22 GB of VRAM at 8 k context, so 8 GB VRAM is insufficient.
Does Creative Quants have a license?
No license information is provided in the model metadata.