GE

Gemma4-Garnet-31B

GemmaGGUF by ddh0Updated 2026-04-10
Download on Hugging Face
Parameters30.7B
Context256K
Layers60
Architecturegemma4
Smallest quant14.7 GB
Quick answer

Gemma4-Garnet-31B needs about 55.8 GB of memory at its main file (a 23.1 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 9 quants, from 14.7 GB to 61.4 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 128.8 GB.

Gemma4-Garnet-31B is a 30.7B-parameter Gemma model in GGUF format, quantized by ddh0. Its trained context length is 256K tokens. The repository has 9 quant files, from 14.7 GB to 61.4 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—14.7 GB 47.4 GB
Too big Get file →
—15.5 GB 48.2 GB
Too big Get file →
—17.9 GB 50.6 GB
Too big Get file →
—19.3 GB 52.0 GB
Too big Get file →
—23.1 GB 55.8 GB
Too big Get file →
—25.8 GB 58.5 GB
Too big Get file →
—29.3 GB 62.0 GB
Too big Get file →
—32.6 GB 65.3 GB
Too big Get file →
BF1661.4 GB 94.1 GB
Too big Get file →

What GPU do you need for Gemma4-Garnet-31B?

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: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: no quant fits at an 8K context.
  • 32 GB VRAM: no quant fits at an 8K context.
  • 48 GB VRAM: the best quant that fits is the main file (14.7 GB file, about 47.4 GB in use).

Which Gemma4-Garnet-31B quant should you choose?

If memory is tight, the smallest file is the first one in the table at 14.7 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegemma4
Parameters30.7B
Layers60
Trained context262,144 tokens
KV cache (fp16)3840 KB per token

Source

Quantized byddh0
FamilyGemma
Licenseapache-2.0
Downloads (HF)92
Last updated2026-04-10

Frequently asked questions about Gemma4-Garnet-31B

How much VRAM does Gemma4-Garnet-31B need?

About 55.8 GB at its main file with an 8K context window. That is the 23.1 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-Garnet-31B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 47.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Gemma4-Garnet-31B GGUF?

It depends on the quant: file is 14.7 GB, file is 15.5 GB, file is 17.9 GB, file is 19.3 GB, file is 23.1 GB, file is 25.8 GB and 3 more.

What context length does Gemma4-Garnet-31B support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 32.2 GB at 8K and 128.8 GB at 32K.

Where can I download Gemma4-Garnet-31B GGUF?

The files are on Hugging Face in the ddh0/Gemma4-Garnet-31B-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 Gemma4-Garnet-31B 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 ddh0

All by ddh0 →

More Gemma models

All Gemma →

Other medium models

All medium models →