GE

gemma 4 12B it qat uncensored heretic UDmerge

GemmaGGUF by EZForeverUpdated 2026-07-20
Download on Hugging Face
Parameters11.9B
Context256K
Layers48
Architecturegemma4
Smallest quant6.7 GB
Quick answer

gemma 4 12B it qat uncensored heretic UDmerge needs about 20.1 GB of memory at Q4_K_XL (a 6.7 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 2 quants, from 6.7 GB (Q4_K_XL) to 6.8 GB (Q4_K). Longer context needs more: at 32K tokens the KV cache alone adds about 51.5 GB.

Gemma 4 12B it QAT Uncensored Heretic UDmerge – 11.9B parameter LLM

Gemma 4 12B it QAT Uncensored Heretic UDmerge is a 11.9B parameter model from the Gemma family. It supports reasoning, tools, and vision. The model is available in two GGUF quantizations, Q4_K_XL and Q4_K.

Good at

  • Reasoning tasks
  • Tool usage
  • Vision queries

Limits

  • Requires ~20GB VRAM at 8k context
  • License: apache-2.0
  • No explicit support for larger context beyond 262144 tokens

Best for

  • Chatbot development
  • Multimodal content creation
  • Tool‑integrated workflows

Who it’s for. Developers building chat or multimodal applications who need a large‑parameter model with uncensored behavior and tool support. The model is suitable for users with sufficient GPU memory to run the quantized variants.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_XL6.7 GB 20.1 GB
Too big Get file →
Q4_K6.8 GB 20.2 GB
Too big Get file →

For 8‑GB VRAM, the model is not feasible. With 20‑GB VRAM, use Q4_K_XL (6.72 GB file, 20.1 GB memory) or Q4_K (6.81 GB file, 20.2 GB memory). The memory estimates are approximate and depend on context size.

What GPU do you need for gemma 4 12B it qat uncensored heretic UDmerge?

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 (6.8 GB file, about 20.2 GB in use).

Which gemma 4 12B it qat uncensored heretic UDmerge quant should you choose?

Q4_K_XL (6.7 GB) is the middle option in this repository. 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

Architecturegemma4
Parameters11.9B
Layers48
Trained context262,144 tokens
KV cache (fp16)1536 KB per token

Frequently asked questions about gemma 4 12B it qat uncensored heretic UDmerge

How much VRAM does gemma 4 12B it qat uncensored heretic UDmerge need?

About 20.1 GB at Q4_K_XL with an 8K context window. That is the 6.7 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 gemma 4 12B it qat uncensored heretic UDmerge on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 20.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of gemma 4 12B it qat uncensored heretic UDmerge GGUF?

It depends on the quant: Q4_K_XL is 6.7 GB, Q4_K is 6.8 GB.

What context length does gemma 4 12B it qat uncensored heretic UDmerge 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 gemma 4 12B it qat uncensored heretic UDmerge GGUF?

The files are on Hugging Face in the EZForever/gemma-4-12B-it-qat-uncensored-heretic-UDmerge-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 gemma 4 12B it qat uncensored heretic UDmerge 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 model requires approximately 20 GB VRAM at 8k context for either quantization.

Does the model support vision tasks?

Yes. Detected abilities include vision, allowing image input processing.

What license applies to this model?

The model is released under the apache-2.0 license.

Other GGUFs of gemma-4-12B-it-qat-q4_0-unquantized-uncensored-heretic

Similar models

Browse all →

More from EZForever

All by EZForever →

More Gemma models

All Gemma →

Other medium models

All medium models →