GE

Gemma 4 E4B It Uncensored Heretic

GemmaGGUF by OS-SoftwareUpdated 2026-09-15
Download on Hugging Face
Parameters7.46B
Context128K
Layers42
Architecturegemma4
Smallest quant3.7 GB
Quick answer

Gemma 4 E4B It Uncensored Heretic needs about 7.0 GB of memory at Q4_K_XL (a 5.1 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 6 quants, from 3.7 GB (Q2_K_XL) to 8.6 GB (Q8_K_XL). Longer context needs more: at 32K tokens the KV cache alone adds about 5.6 GB.

Gemma 4 E4B It Uncensored Heretic – 7.46B multimodal LLM

Gemma 4 E4B It Uncensored Heretic is a 7.46B parameter model with a 131072 token context window. It supports text and image input and is instruction‑tuned for research use. The model is released under Apache‑2.0 and is unaligned for safety.

Good at

  • Multimodal text and image understanding
  • Large context reasoning
  • Instruction‑tuned generation

Limits

  • Unaligned safety – may produce harmful content
  • No audio support in this variant
  • Requires research‑grade usage

Best for

  • Research and safety studies
  • Red‑team testing
  • Multimodal prototyping

Who it’s for. Researchers and developers needing a large multimodal model for experimentation. The model is intended for safety research, alignment studies, and red‑team testing, not for public deployment.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K_XL3.7 GB 5.6 GB
Fits Get file →
Q3_K_XL4.6 GB 6.5 GB
Fits Get file →
Q4_K_XL5.1 GB 7.0 GB
Fits Get file →
Q5_K_XL6.6 GB 8.5 GB
Too big Get file →
Q6_K_XL7.4 GB 9.3 GB
Too big Get file →
Q8_K_XL8.6 GB 10.5 GB
Too big Get file →

For 8 GB VRAM, use Q2_K_XL (file size 3.73 GB, estimated 5.6 GB memory). For 12 GB VRAM, Q3_K_XL (4.55 GB, 6.5 GB memory). For 16 GB VRAM, Q4_K_XL (5.08 GB, 7 GB memory). Memory estimates are approximate.

What GPU do you need for Gemma 4 E4B It 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: the best quant that fits is Q2_K_XL (3.7 GB file, about 5.6 GB in use).
  • 8 GB VRAM: the best quant that fits is Q4_K_XL (5.1 GB file, about 7.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_K_XL (8.6 GB file, about 10.5 GB in use).

Which Gemma 4 E4B It Uncensored Heretic quant should you choose?

Q4_K_XL (5.1 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 Q2_K_XL at 3.7 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegemma4
Parameters7.46B
Layers42
Trained context131,072 tokens
KV cache (fp16)168 KB per token

Source

Quantized byOS-Software
FamilyGemma
Licenseapache-2.0
Downloads (HF)3,179
Last updated2026-09-15

Frequently asked questions about Gemma 4 E4B It Uncensored Heretic

How much VRAM does Gemma 4 E4B It Uncensored Heretic need?

About 7.0 GB at Q4_K_XL with an 8K context window. That is the 5.1 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 E4B It Uncensored Heretic on an 8 GB GPU?

Yes, with Q4_K_XL: the 5.1 GB file needs about 7.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Gemma 4 E4B It Uncensored Heretic GGUF?

It depends on the quant: Q2_K_XL is 3.7 GB, Q3_K_XL is 4.6 GB, Q4_K_XL is 5.1 GB, Q5_K_XL is 6.6 GB, Q6_K_XL is 7.4 GB, Q8_K_XL is 8.6 GB.

What context length does Gemma 4 E4B It Uncensored Heretic support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.4 GB at 8K and 5.6 GB at 32K.

Where can I download Gemma 4 E4B It Uncensored Heretic GGUF?

The files are on Hugging Face in the OS-Software/gemma-4-E4B-it-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 E4B It 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 Gemma 4 E4B It Uncensored Heretic on 8 GB VRAM?

Yes, the Q2_K_XL quantized version requires about 5.6 GB memory at 8 k context, fitting within 8 GB VRAM.

Does this model support audio input?

No, audio is only supported on the E2B, E4B, and 12B models in other variants; this variant handles text and image.

What license applies to this model?

The model is released under the Apache‑2.0 license, with the base model’s rights retained by Google DeepMind.

Other GGUFs of gemma-4-E4B

Similar models

Browse all →

More from OS-Software

All by OS-Software →

More Gemma models

All Gemma →

Other small models

All small models →