GE

gemma4 pure

GemmaGGUF by macolombUpdated 2026-05-11
Download on Hugging Face
Parameters4.65B
Context128K
Layers35
Architecturegemma4
Smallest quant2.7 GB
Quick answer

gemma4 pure needs about 3.7 GB of memory at Q4_0 (a 2.7 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 2.7 GB (IQ4_NL) to 4.3 GB (Q4_0). Longer context needs more: at 32K tokens the KV cache alone adds about 2.3 GB.

gemma4 pure is a 4.65B-parameter Gemma model in GGUF format, quantized by macolomb. Its trained context length is 128K tokens. The repository has 4 quant files, from 2.7 GB (IQ4_NL) to 4.3 GB (Q4_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ4_NL2.7 GB 3.7 GB
Fits Get file →
Q4_02.7 GB 3.7 GB
Fits Get file →
Q4_04.0 GB 5.1 GB
Fits Get file →
Q4_04.3 GB 5.4 GB
Fits Get file →

What GPU do you need for gemma4 pure?

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 (2.7 GB file, about 3.7 GB in use).
  • 6 GB VRAM: the best quant that fits is Q4_0 (4.3 GB file, about 5.4 GB in use).

Which gemma4 pure quant should you choose?

Q4_0 (2.7 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 IQ4_NL at 2.7 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
Parameters4.65B
Layers35
Trained context131,072 tokens
KV cache (fp16)70 KB per token

Source

Quantized bymacolomb
FamilyGemma
Licenseapache-2.0
Downloads (HF)10
Last updated2026-05-11

Frequently asked questions about gemma4 pure

How much VRAM does gemma4 pure need?

About 3.7 GB at Q4_0 with an 8K context window. That is the 2.7 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 gemma4 pure on an 8 GB GPU?

Yes, with Q4_0: the 4.3 GB file needs about 5.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of gemma4 pure GGUF?

It depends on the quant: IQ4_NL is 2.7 GB, Q4_0 is 2.7 GB, Q4_0 is 4.0 GB, Q4_0 is 4.3 GB.

What context length does gemma4 pure 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 gemma4 pure GGUF?

The files are on Hugging Face in the macolomb/gemma4-pure repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does gemma4 pure 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.

Similar models

Browse all →

More from macolomb

All by macolomb →

More Gemma models

All Gemma →

Other small models

All small models →