GE

gemma 4 E4B it qat q4 0 heretic

GemmaGGUF by FadedRedStarUpdated 2026-07-11
Download on Hugging Face
Parameters7.46B
Context128K
Layers4
Architecturegemma4-assistant
Smallest quant0.1 GB
Quick answer

gemma 4 E4B it qat q4 0 heretic needs about 0.8 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 4.3 GB (Q4_0). Longer context needs more: at 32K tokens the KV cache alone adds about 0.5 GB.

Gemma 4 E4B QAT Q4_0 Heretic – 7.46B parameter LLM

Gemma 4 E4B is a 7.46B parameter multimodal model trained with Quantization‑Aware Training. It supports text, image, and audio input and outputs text. The model uses a 131072‑token context window and is available in a single Q4_0 GGUF build.

Good at

  • Multimodal text and image processing
  • Instruction‑tuned coding tasks
  • Reasoning with configurable thinking modes

Limits

  • No vision support in the provided GGUF build
  • Requires Q4_0 quantization only
  • Large memory for 4.26 GB file

Best for

  • Deploying on laptops with 8 GB VRAM
  • Running on servers with limited RAM
  • Fine‑tuning for specific multimodal tasks

Who it’s for. Developers and researchers needing a lightweight, multimodal LLM that retains near‑bfloat16 quality after QAT. The model is suitable for environments where memory is constrained but multimodal inference is required.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_00.1 GB 0.7 GB
Fits Get file →
Q4_00.2 GB 0.8 GB
Fits Get file →
Q4_04.3 GB 4.9 GB
Fits Get file →

For 8 GB VRAM use the 0.1 GB Q4_0 file (≈0.7 GB memory at 8 k context). If more context is needed, the 0.17 GB file uses ≈0.8 GB memory. The 4.26 GB file requires ≈4.9 GB memory and is best for servers with ≥8 GB RAM.

What GPU do you need for gemma 4 E4B 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 (0.2 GB file, about 0.8 GB in use).
  • 6 GB VRAM: the best quant that fits is Q4_0 (4.3 GB file, about 4.9 GB in use).

Which gemma 4 E4B 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
Parameters7.46B
Layers4
Trained context131,072 tokens
KV cache (fp16)16 KB per token

Source

Quantized byFadedRedStar
FamilyGemma
Licensegemma
Downloads (HF)1,923
Last updated2026-07-11

Frequently asked questions about gemma 4 E4B it qat q4 0 heretic

How much VRAM does gemma 4 E4B it qat q4 0 heretic need?

About 0.8 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 E4B it qat q4 0 heretic on an 8 GB GPU?

Yes, with Q4_0: the 4.3 GB file needs about 4.9 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 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 4.3 GB.

What context length does gemma 4 E4B 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 0.5 GB at 32K.

Where can I download gemma 4 E4B it qat q4 0 heretic GGUF?

The files are on Hugging Face in the FadedRedStar/gemma-4-E4B-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 E4B 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 build uses about 0.7 GB memory at 8 k context, fitting comfortably in 8 GB VRAM.

Does the GGUF file support vision?

The provided GGUF build includes the vision projection matrix, enabling image input.

What quantization is required?

Only the Q4_0 quantization is supported; other quant formats are incompatible with this QAT model.

Other GGUFs of gemma-4-E4B-it-qat-q4_0-unquantized-heretic

Similar models

Browse all →

More from FadedRedStar

All by FadedRedStar →

More Gemma models

All Gemma →

Other small models

All small models →