Gemma4-12B-Uncensored needs about 20.8 GB of memory at Q4_K_M (a 7.4 GB file) with an 8K context window, so it fits on a 24 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 51.5 GB.
Gemma4-12B-Uncensored, a 12B multimodal research model
Gemma4-12B-Uncensored is a 11.9B parameter Gemma 4 model with full multimodal support. It is released as a clean BF16 checkpoint and includes tokenizer, chat template, and multimodal processor. The model is intended for research and controlled evaluation.
Good at
- Multimodal text and image generation
- Reasoning and tool use
- Controlled refusal behavior
Limits
- No vision support in llama.cpp yet
- Requires separate multimodal projector
- License requires compliance with Gemma terms
Best for
- Research on refusal behavior
- Multimodal instruction following experiments
- Safety benchmark testing
Who it’s for. Researchers and developers working on multimodal LLMs who need a 12B Gemma 4 model with controlled refusal behavior. The model is suitable for controlled evaluation and experimentation under the Gemma license.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 7.4 GB | 20.8 GB | Too big | Get file → |
The Q4_K_M quantization is available at 7.38 GB. It requires approximately 20.8 GB of VRAM at 8 k context. For lower VRAM budgets, consider a higher quantization if available, but only Q4_K_M is provided here.
What GPU do you need for Gemma4-12B-Uncensored?
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 (7.4 GB file, about 20.8 GB in use).
Which Gemma4-12B-Uncensored quant should you choose?
Q4_K_M is the usual starting point for Gemma4-12B-Uncensored: it balances file size and quality well. Here it is a 7.4 GB file.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Gemma4-12B-Uncensored
How much VRAM does Gemma4-12B-Uncensored need?
About 20.8 GB at Q4_K_M with an 8K context window. That is the 7.4 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 Gemma4-12B-Uncensored on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 20.8 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Gemma4-12B-Uncensored GGUF?
It depends on the quant: Q4_K_M is 7.4 GB.
What context length does Gemma4-12B-Uncensored 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 Gemma4-12B-Uncensored GGUF?
The files are on Hugging Face in the toandev/Gemma4-12B-Uncensored-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 Gemma4-12B-Uncensored 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 Gemma4-12B-Uncensored on 8 GB VRAM?
No. The Q4_K_M quantization needs about 20.8 GB of VRAM at 8 k context, so 8 GB is insufficient.
Does this model support vision in llama.cpp?
Vision support is under active development; use the separate multimodal projector GGUF with recent llama.cpp builds.
What license applies to this model?
The model is released under the Gemma license and requires compliance with its terms.