Gemma4 12B Uncensored HauhauCS 1M needs about 1.8 GB of memory at its main file (a 0.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 0.3 GB to 7.4 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
Gemma4 12B Uncensored with 1M context, vision, and MTP
Gemma4 12B Uncensored HauhauCS 1M is a 12B dense model with a 1,048,576-token context baked in. It includes vision support via mmproj and an MTP speculative‑decoding draft head for faster generation. The model is quantization‑aware‑trained for 4‑bit quality.
Good at
- Large context reasoning
- Vision image input
- Speculative decoding speedup
Limits
- No vision without mmproj
- Requires single GPU for stability
- No other quant available
Best for
- Long‑form document analysis
- Image‑based question answering
- Agentic coding tasks
Who it’s for. Developers and researchers needing extended context and vision in a single GGUF model. The model is suitable for applications that benefit from 1M token context and speculative decoding, such as advanced chatbots or content generation pipelines.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.3 GB | 1.8 GB | Fits | Get file → | |
| — | 7.4 GB | 9.0 GB | Too big | Get file → |
For 8 GB VRAM use the 0.25 GB file; it estimates 1.8 GB memory at 8 k context. For 16 GB VRAM use the 7.38 GB file; it estimates 9 GB memory at 8 k context. Both files are quantized to 4‑bit and are the only quants available.
What GPU do you need for Gemma4 12B Uncensored HauhauCS 1M?
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: the best quant that fits is the main file (0.3 GB file, about 1.8 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.3 GB file, about 1.8 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.3 GB file, about 1.8 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (7.4 GB file, about 9.0 GB in use).
Specifications
Architecture from the GGUF header
Frequently asked questions about Gemma4 12B Uncensored HauhauCS 1M
How much VRAM does Gemma4 12B Uncensored HauhauCS 1M need?
About 1.8 GB at its main file with an 8K context window. That is the 0.3 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 HauhauCS 1M on an 8 GB GPU?
Yes, with the smaller files: the 0.3 GB file needs about 1.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Gemma4 12B Uncensored HauhauCS 1M GGUF?
It depends on the quant: file is 0.3 GB, file is 7.4 GB.
What context length does Gemma4 12B Uncensored HauhauCS 1M support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.
Where can I download Gemma4 12B Uncensored HauhauCS 1M GGUF?
The files are on Hugging Face in the satgeze/Gemma4-12B-Uncensored-HauhauCS-1M-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 HauhauCS 1M 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 this model on 8 GB VRAM?
Yes, using the 0.25 GB quant file which estimates 1.8 GB memory at 8 k context.
Does it support vision?
Yes, load the mmproj alongside the model for image input.
Is there a faster decoding option?
Yes, the included MTP speculative‑decoding draft head offers ~51% speedup over standard decoding.