GE

Gemma 4 31B It Qat Q4_0 Uncensored Heretic

GemmaGGUF by OS-SoftwareUpdated 2026-09-08
Download on Hugging Face
Parameters30.7B
Context256K
Layers60
Architecturegemma4
Smallest quant17.3 GB
Quick answer

Gemma 4 31B It Qat Q4_0 Uncensored Heretic needs about 50.0 GB of memory at Q4_0 (a 17.3 GB file) with an 8K context window, which is more than a 48 GB GPU holds. Longer context needs more: at 32K tokens the KV cache alone adds about 128.8 GB.

Gemma 4 31B It Qat Q4_0 Uncensored Heretic – 30.7B parameter multimodal model

Gemma 4 31B It Qat Q4_0 Uncensored Heretic is a 30.7B parameter multimodal model. It supports text and image input and generates text output. The model is released under Apache 2.0 and is intended for research and experimentation only.

Good at

  • Multimodal text and image processing
  • Large context up to 262144 tokens
  • Reasoning and coding tasks

Limits

  • No safety alignment – may produce harmful content
  • Requires 50 GB VRAM at 8K context
  • Not for public or end‑user services

Best for

  • Research on multimodal reasoning
  • Safety and alignment studies
  • Red‑team testing

Who it’s for. Researchers and developers who need a large multimodal model for experimentation and safety research. The model is not suitable for production or public deployment.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_017.3 GB 50.0 GB
Too big Get file →

For 8 GB VRAM use Q4_0 which requires 50 GB VRAM at 8K context – this is not feasible on 8 GB. For larger GPUs, Q4_0 is the only available quant and will need at least 50 GB VRAM. The file size is 17.29 GB.

What GPU do you need for Gemma 4 31B It Qat Q4_0 Uncensored Heretic?

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: no quant fits at an 8K context.
  • 32 GB VRAM: no quant fits at an 8K context.
  • 48 GB VRAM: no quant fits at an 8K context.

Which Gemma 4 31B It Qat Q4_0 Uncensored Heretic quant should you choose?

Q4_0 (17.3 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
Parameters30.7B
Layers60
Trained context262,144 tokens
KV cache (fp16)3840 KB per token

Source

Quantized byOS-Software
FamilyGemma
Licenseapache-2.0
Downloads (HF)3,005
Last updated2026-09-08

Frequently asked questions about Gemma 4 31B It Qat Q4_0 Uncensored Heretic

How much VRAM does Gemma 4 31B It Qat Q4_0 Uncensored Heretic need?

About 50.0 GB at Q4_0 with an 8K context window. That is the 17.3 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 Gemma 4 31B It Qat Q4_0 Uncensored Heretic on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 50.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Gemma 4 31B It Qat Q4_0 Uncensored Heretic GGUF?

It depends on the quant: Q4_0 is 17.3 GB.

What context length does Gemma 4 31B It Qat Q4_0 Uncensored Heretic support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 32.2 GB at 8K and 128.8 GB at 32K.

Where can I download Gemma 4 31B It Qat Q4_0 Uncensored Heretic GGUF?

The files are on Hugging Face in the OS-Software/gemma-4-31B-it-qat-q4_0-uncensored-heretic-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 31B It Qat Q4_0 Uncensored Heretic 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 Q4_0 quant requires 50 GB VRAM at 8K context, so 8 GB is insufficient.

Is this model safe for production use?

No. The model has reduced safety alignment and is intended only for research and experimentation.

What license applies to this model?

Apache 2.0. The model is released under the base model’s license and is for research use only.

Other GGUFs of gemma-4-31B-it

Similar models

Browse all →

More from OS-Software

All by OS-Software →

More Gemma models

All Gemma →

Other medium models

All medium models →