GE

gemma 4 E2B it qat q4 0 heretic

GemmaGGUF by FadedRedStarUpdated 2026-07-11
Download on Hugging Face
Parameters4.63B
Context128K
Layers4
Architecturegemma4-assistant
Smallest quant0.1 GB
Quick answer

gemma 4 E2B it qat q4 0 heretic needs about 0.7 GB of memory at Q4_0 (a 0.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 0.1 GB (Q4_0) to 2.6 GB (Q4_0). Longer context needs more: at 32K tokens the KV cache alone adds about 0.3 GB.

Gemma 4 E2B it QAT Q4_0 Heretic – 4.63B parameter multimodal model

Gemma 4 E2B it QAT Q4_0 Heretic is a 4.63B parameter model from the Gemma 4 family. It supports text, image, and audio input and outputs text. The model was quantized with Quantization‑Aware Training and post‑processed with Heretic ARA to reduce refusal behavior.

Good at

  • Text generation
  • Coding
  • Multimodal reasoning

Limits

  • No vision support in this GGUF build
  • Requires 8k context for memory estimates
  • License: gemma

Best for

  • Chat assistants
  • Code generation tools
  • Multimodal content creation

Who it’s for. Developers and researchers needing a compact, multimodal LLM that can run on limited hardware. The QAT‑trained weights preserve quality while reducing memory footprint.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_00.1 GB 0.7 GB
Fits Get file →
Q4_00.2 GB 0.7 GB
Fits Get file →
Q4_02.6 GB 3.2 GB
Fits Get file →

For 8 GB VRAM, use the 0.1 GB Q4_0 file (est. 0.7 GB memory at 8k context). For 16 GB VRAM, the 0.17 GB file is also suitable. If more memory is available, the 2.64 GB file gives the full model size with 3.2 GB memory at 8k context.

What GPU do you need for gemma 4 E2B it qat q4 0 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: the best quant that fits is Q4_0 (2.6 GB file, about 3.2 GB in use).

Which gemma 4 E2B it qat q4 0 heretic quant should you choose?

Q4_0 (0.2 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 0.1 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-assistant
Parameters4.63B
Layers4
Trained context131,072 tokens
KV cache (fp16)8 KB per token

Source

Quantized byFadedRedStar
FamilyGemma
Licensegemma
Downloads (HF)2,425
Last updated2026-07-11

Frequently asked questions about gemma 4 E2B it qat q4 0 heretic

How much VRAM does gemma 4 E2B it qat q4 0 heretic need?

About 0.7 GB at Q4_0 with an 8K context window. That is the 0.2 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 E2B it qat q4 0 heretic on an 8 GB GPU?

Yes, with Q4_0: the 2.6 GB file needs about 3.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of gemma 4 E2B it qat q4 0 heretic GGUF?

It depends on the quant: Q4_0 is 0.1 GB, Q4_0 is 0.2 GB, Q4_0 is 2.6 GB.

What context length does gemma 4 E2B it qat q4 0 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 0.1 GB at 8K and 0.3 GB at 32K.

Where can I download gemma 4 E2B it qat q4 0 heretic GGUF?

The files are on Hugging Face in the FadedRedStar/gemma-4-E2B-it-qat-q4_0-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 E2B it qat q4 0 heretic 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, the 0.1 GB Q4_0 file uses about 0.7 GB memory at 8k context, fitting within 8 GB VRAM.

Does this model support vision?

The GGUF build does not include vision support; it handles text, image, and audio input only.

What license applies to this model?

The model is licensed under the gemma license, as specified in the parent model card.

Similar models

Browse all →

More from FadedRedStar

All by FadedRedStar →

More Gemma models

All Gemma →

Other small models

All small models →