GE

gemma-4-E4B

GemmaGGUF by ggml-orgUpdated 2026-10-19
Download on Hugging Face
Parameters7.52B
Context128K
Layers42
Architecturegemma4
Smallest quant8.0 GB
Quick answer

gemma-4-E4B needs about 9.9 GB of memory at Q8_0 (a 8.0 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 2 quants, from 8.0 GB (Q8_0) to 15.1 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 5.6 GB.

Gemma‑4 E4B: 7.52B‑parameter text model with 256K context

Gemma‑4 E4B is a 7.52B‑parameter model from Google DeepMind. It supports a 256K‑token context window and is available in GGUF format. The model is licensed under Apache‑2.0 and is designed for local inference.

Good at

  • Large‑context text generation
  • Reasoning tasks
  • Multilingual support

Limits

  • No vision or audio support in this variant
  • Requires 8.03 GB for Q8_0 or 15.05 GB for BF16
  • Memory estimate 9.9 GB at 8K context for Q8_0

Best for

  • Chatbots needing long context
  • Code generation with reasoning
  • Local deployment on laptops

Who it’s for. Developers and researchers who need a high‑capacity text model that can run locally. The model is suitable for edge devices with sufficient VRAM and for server‑side inference where a large context window is beneficial.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_08.0 GB 9.9 GB
Too big Get file →
BF1615.1 GB 17.0 GB
Too big Get file →

For 8 GB VRAM, use the Q8_0 quantized file (8.03 GB). If you have 16 GB VRAM, the BF16 file (15.05 GB) is also viable. Memory estimates are approximate and depend on batch size.

What GPU do you need for gemma-4-E4B?

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: no quant fits at an 8K context.
  • 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 BF16 (15.1 GB file, about 17.0 GB in use).

Which gemma-4-E4B quant should you choose?

Q8_0 (8.0 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

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 byggml-org
FamilyGemma
Licenseapache-2.0
Downloads (HF)924
Last updated2026-10-19

Frequently asked questions about gemma-4-E4B

How much VRAM does gemma-4-E4B need?

About 9.9 GB at Q8_0 with an 8K context window. That is the 8.0 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 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of gemma-4-E4B GGUF?

It depends on the quant: Q8_0 is 8.0 GB, BF16 is 15.1 GB.

What context length does gemma-4-E4B 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 GGUF?

The files are on Hugging Face in the ggml-org/gemma-4-E4B-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 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 on 8 GB VRAM?

Yes, the Q8_0 quantized file is 8.03 GB, which fits into 8 GB VRAM with some overhead.

Does this model support image input?

No, the E4B variant does not include vision or audio capabilities.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of gemma-4-E4B

Similar models

Browse all →

More from ggml-org

All by ggml-org →

More Gemma models

All Gemma →

Other small models

All small models →