GE

Gemma 4 E4B Base Heretic

GemmaGGUF by mradermacherUpdated 2026-10-28
Download on Hugging Face
Parameters7.52B
Context128K
Layers42
Architecturegemma4
Smallest quant4.4 GB
Quick answer

Gemma 4 E4B Base Heretic needs about 7.2 GB of memory at Q4_K_M (a 5.3 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 12 quants, from 4.4 GB (Q2_K) to 15.1 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 5.6 GB.

Gemma 4 E4B Base Heretic – 7.52B parameter base model

Gemma 4 E4B Base Heretic is a 7.52B parameter model from the Gemma family. It is a representation‑engineering ablation of the base Gemma 4 E4B model, released under the apache‑2.0 license. The model supports a 131072 token context window and has no built‑in chat template.

Good at

  • Large context handling
  • Low‑latency inference on modest VRAM
  • Fine‑tuning with LoRA

Limits

  • No instruction tuning; requires custom chat template
  • Large VRAM needed for evaluation
  • No vision or audio support

Best for

  • Research on representation learning
  • Fine‑tuning for domain‑specific tasks
  • Benchmarking low‑precision quantization

Who it’s for. Researchers and developers who need a base Gemma 4 model for custom instruction tuning or fine‑tuning. The model is suitable for those who prefer to build their own chat interface and are comfortable managing evaluation on high‑VRAM GPUs.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K4.4 GB 6.3 GB
Fits Get file →
Q3_K_S4.7 GB 6.6 GB
Fits Get file →
Q3_K_M4.9 GB 6.8 GB
Fits Get file →
Q3_K_L5.0 GB 6.9 GB
Fits Get file →
IQ4_XS5.1 GB 7.0 GB
Fits Get file →
Q4_K_S5.2 GB 7.1 GB
Fits Get file →
Q4_K_M5.3 GB 7.2 GB
Tight Get file →
Q5_K_S5.7 GB 7.6 GB
Tight Get file →
Q5_K_M5.8 GB 7.7 GB
Tight Get file →
Q6_K6.2 GB 8.1 GB
Too big Get file →
Q8_08.0 GB 9.9 GB
Too big Get file →
F1615.1 GB 17.0 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (5.34 GB file, 7.2 GB memory) or IQ4_XS (5.09 GB file, 7 GB memory). If 16 GB VRAM is available, Q5_K_M (5.76 GB file, 7.7 GB memory) offers higher precision. For the lowest memory footprint, Q2_K (4.4 GB file, 6.3 GB memory) is recommended, though precision is reduced.

What GPU do you need for Gemma 4 E4B Base 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: no quant fits at an 8K context.
  • 8 GB VRAM: the best quant that fits is Q5_K_M (5.8 GB file, about 7.7 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (8.0 GB file, about 9.9 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (8.0 GB file, about 9.9 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (15.1 GB file, about 17.0 GB in use).

Which Gemma 4 E4B Base Heretic quant should you choose?

Q4_K_M is the usual starting point for Gemma 4 E4B Base Heretic: it balances file size and quality well. Here it is a 5.3 GB file.

The Q8_0 file is 8.0 GB, about 1.5 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 Q2_K at 4.4 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
Parameters7.52B
Layers42
Trained context131,072 tokens
KV cache (fp16)168 KB per token

Source

Quantized bymradermacher
FamilyGemma
Licenseapache-2.0
Downloads (HF)656
Last updated2026-10-28

Frequently asked questions about Gemma 4 E4B Base Heretic

How much VRAM does Gemma 4 E4B Base Heretic need?

About 7.2 GB at Q4_K_M with an 8K context window. That is the 5.3 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 Base Heretic on an 8 GB GPU?

Yes, with Q5_K_M: the 5.8 GB file needs about 7.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

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

It depends on the quant: Q2_K is 4.4 GB, Q3_K_S is 4.7 GB, Q3_K_M is 4.9 GB, Q3_K_L is 5.0 GB, IQ4_XS is 5.1 GB, Q4_K_S is 5.2 GB and 6 more.

What context length does Gemma 4 E4B Base 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 Base Heretic GGUF?

The files are on Hugging Face in the mradermacher/gemma-4-E4B-base-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 Base 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 this model on 8 GB VRAM?

Yes, using Q4_K_M or IQ4_XS quantizations will fit within 8 GB VRAM, with approximate memory usage of 7.2 GB and 7 GB respectively.

Does this model support chat out of the box?

No, the base model has no chat template. A custom chat template must be added before conversational use.

Is vision support available?

No, the model does not include vision or audio encoders; only the text transformer is present.

Other GGUFs of gemma-4-E4B-base-heretic

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Gemma models

All Gemma →

Other small models

All small models →