GE

Gemma 4 E2B Heretic

GemmaGGUF by DuoNeuralUpdated 2026-05-03
Download on Hugging Face
Parameters4.63B
Context128K
Layers35
Architecturegemma4
Smallest quant2.3 GB
Quick answer

Gemma 4 E2B Heretic needs about 4.5 GB of memory at Q4_K_M (a 3.4 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 10 quants, from 2.3 GB (IQ1_S) to 9.3 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 2.3 GB.

Gemma 4 E2B Heretic – 4.63B parameter model with 128K context

Gemma 4 E2B Heretic is a 4.63B parameter model quantized by DuoNeural. It supports a 131072 token context and is released under the apache-2.0 license. The model is a 2B Instruct variant with abliteration to remove refusal behavior.

Good at

  • Large context handling
  • Instruction following
  • Reasoning

Limits

  • No vision support
  • No mixture of experts
  • Requires 8k context for memory estimates

Best for

  • Chatbots needing long context
  • Instruction‑driven applications
  • Research prototyping

Who it’s for. Developers and researchers who need a 4B‑level Gemma model with extended context and instruction‑following capabilities. The model is suitable for local deployment using llama.cpp or compatible tools.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S2.3 GB 3.4 GB
Fits Get file →
IQ2_M2.6 GB 3.6 GB
Fits Get file →
IQ3_XXS2.6 GB 3.7 GB
Fits Get file →
Q3_K_M3.2 GB 4.3 GB
Fits Get file →
IQ4_XS3.3 GB 4.4 GB
Fits Get file →
Q4_K_M3.4 GB 4.5 GB
Fits Get file →
Q5_K_M3.6 GB 4.7 GB
Fits Get file →
Q6_K3.8 GB 4.9 GB
Fits Get file →
Q8_04.9 GB 6.0 GB
Fits Get file →
—9.3 GB 10.4 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (2.32 GB file, 3.4 GB memory) or IQ2_M (2.55 GB file, 3.6 GB memory). For 12 GB VRAM, Q4_K_M (3.42 GB file, 4.5 GB memory) is recommended. Higher‑quality quants like Q8_0 (4.95 GB file, 6 GB memory) need 16 GB VRAM or more.

What GPU do you need for Gemma 4 E2B 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 IQ3_XXS (2.6 GB file, about 3.7 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (4.9 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (4.9 GB file, about 6.0 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (9.3 GB file, about 10.4 GB in use).

Which Gemma 4 E2B Heretic quant should you choose?

Q4_K_M is the usual starting point for Gemma 4 E2B Heretic: it balances file size and quality well. Here it is a 3.4 GB file.

The Q8_0 file is 4.9 GB, about 1.4 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is IQ1_S at 2.3 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
Parameters4.63B
Layers35
Trained context131,072 tokens
KV cache (fp16)70 KB per token

Source

Quantized byDuoNeural
FamilyGemma
Licenseapache-2.0
Downloads (HF)1,255
Last updated2026-05-03

Frequently asked questions about Gemma 4 E2B Heretic

How much VRAM does Gemma 4 E2B Heretic need?

About 4.5 GB at Q4_K_M with an 8K context window. That is the 3.4 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 E2B Heretic on an 8 GB GPU?

Yes, with Q8_0: the 4.9 GB file needs about 6.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Gemma 4 E2B Heretic GGUF?

It depends on the quant: IQ1_S is 2.3 GB, IQ2_M is 2.6 GB, IQ3_XXS is 2.6 GB, Q3_K_M is 3.2 GB, IQ4_XS is 3.3 GB, Q4_K_M is 3.4 GB and 4 more.

What context length does Gemma 4 E2B 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 0.6 GB at 8K and 2.3 GB at 32K.

Where can I download Gemma 4 E2B Heretic GGUF?

The files are on Hugging Face in the DuoNeural/Gemma-4-E2B-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 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 E2B Heretic on 8 GB VRAM?

Yes, the IQ1_S and IQ2_M quants fit within 8 GB VRAM with estimated memory usage of 3.4–3.6 GB at 8k context.

Does this model support vision inputs?

No, the model does not have vision capabilities.

What license applies to this model?

The model is released under the apache-2.0 license.

Similar models

Browse all →

More from DuoNeural

All by DuoNeural →

More Gemma models

All Gemma →

Other small models

All small models →