GE

Gemma 4 12B It Qat Q4_0 Unquantized Heretic v1.1

GemmaGGUF by igorlsUpdated 2026-06-07
Download on Hugging Face
Parameters11.9B
Context256K
Layers48
Architecturegemma4
Smallest quant7.0 GB
Quick answer

Gemma 4 12B It Qat Q4_0 Unquantized Heretic v1.1 needs about 20.8 GB of memory at Q4_0 (a 7.4 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 3 quants, from 7.0 GB (Q4_0) to 12.7 GB (Q4_0). Longer context needs more: at 32K tokens the KV cache alone adds about 51.5 GB.

Gemma 4 12B It Qat Q4_0 Unquantized Heretic v1.1 – a decensored 12B thinking model

Gemma 4 12B It Qat Q4_0 Unquantized Heretic v1.1 is a 11.9 billion‑parameter model from the Gemma family. It is a QAT‑Q4_0 checkpoint with Heretic decensoring, released under Apache‑2.0. The model is a thinking model with safety guardrails removed.

Good at

  • Large context handling
  • High‑quality reasoning
  • Fast inference on 4‑bit quant

Limits

  • No safety alignment – requires user filtering
  • No vision support
  • Requires Gemma‑4 architecture support

Best for

  • Research on chain‑of‑thought models
  • Evaluation of decensored behavior
  • Custom safety‑filtered applications

Who it’s for. Researchers, developers, and advanced users who need a 12B Gemma model without safety guardrails and who can implement their own filtering. The model is intended for adults (18+) and for lawful creative use.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_07.0 GB 20.4 GB
Too big Get file →
Q4_07.4 GB 20.8 GB
Too big Get file →
Q4_012.7 GB 26.1 GB
Too big Get file →

For 8 GB VRAM use the 6.98 GB Q4_0 file (≈20.4 GB RAM at 8 k context). For 12 GB VRAM use the 7.38 GB Q4_0 file (≈20.8 GB RAM). For 16 GB VRAM use the 12.67 GB Q4_0 file (≈26.1 GB RAM). Memory estimates are approximate.

What GPU do you need for Gemma 4 12B It Qat Q4_0 Unquantized Heretic v1.1?

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_0 (7.4 GB file, about 20.8 GB in use).
  • 32 GB VRAM: the best quant that fits is Q4_0 (12.7 GB file, about 26.1 GB in use).

Which Gemma 4 12B It Qat Q4_0 Unquantized Heretic v1.1 quant should you choose?

Q4_0 (7.4 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

If memory is tight, the smallest file is Q4_0 at 7.0 GB, with the quality trade-offs that come with fewer bits. 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

Source

Quantized byigorls
FamilyGemma
Licenseapache-2.0
Downloads (HF)2,098
Last updated2026-06-07

Frequently asked questions about Gemma 4 12B It Qat Q4_0 Unquantized Heretic v1.1

How much VRAM does Gemma 4 12B It Qat Q4_0 Unquantized Heretic v1.1 need?

About 20.8 GB at Q4_0 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 Gemma 4 12B It Qat Q4_0 Unquantized Heretic v1.1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 20.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Gemma 4 12B It Qat Q4_0 Unquantized Heretic v1.1 GGUF?

It depends on the quant: Q4_0 is 7.0 GB, Q4_0 is 7.4 GB, Q4_0 is 12.7 GB.

What context length does Gemma 4 12B It Qat Q4_0 Unquantized Heretic v1.1 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 Q4_0 Unquantized Heretic v1.1 GGUF?

The files are on Hugging Face in the igorls/gemma-4-12B-it-qat-q4_0-unquantized-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 12B It Qat Q4_0 Unquantized Heretic v1.1 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?

Yes, using the 6.98 GB Q4_0 file will fit 8 GB VRAM, but RAM usage will be about 20.4 GB at 8 k context.

Does this model have vision capabilities?

No, it only supports text input and output.

Is there any safety alignment built into the model?

No, the safety guardrails have been removed; user‑implemented filtering is required.

Similar models

Browse all →

More from igorls

All by igorls →

More Gemma models

All Gemma →

Other medium models

All medium models →