GE

Gemma3_27B

GemmaGGUF by sleeping-aiUpdated 2025-05-17
Download on Hugging Face
Parameters27B
Context128K
Layers62
Architecturegemma3
Smallest quant9.4 GB
Quick answer

Gemma3_27B needs about 14.1 GB of memory at TQ2_0 (a 9.4 GB file) with an 8K context window, so it fits on a 16 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 16.6 GB.

Gemma3_27B is a 27B-parameter Gemma model in GGUF format, quantized by sleeping-ai. Its trained context length is 128K tokens. The repository has 1 quant file, from 9.4 GB (TQ2_0) to 9.4 GB (TQ2_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
TQ2_09.4 GB 14.1 GB
Too big Get file →

What GPU do you need for Gemma3_27B?

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: the best quant that fits is TQ2_0 (9.4 GB file, about 14.1 GB in use).

Which Gemma3_27B quant should you choose?

TQ2_0 (9.4 GB) is the middle option in this repository. Lower bit counts mean smaller files and more quality loss.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegemma3
Parameters27B
Layers62
Trained context131,072 tokens
KV cache (fp16)496 KB per token

Source

Quantized bysleeping-ai
FamilyGemma
Licensemit
Downloads (HF)27
Last updated2025-05-17

Frequently asked questions about Gemma3_27B

How much VRAM does Gemma3_27B need?

About 14.1 GB at TQ2_0 with an 8K context window. That is the 9.4 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 Gemma3_27B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 14.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Gemma3_27B GGUF?

It depends on the quant: TQ2_0 is 9.4 GB.

What context length does Gemma3_27B support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 4.2 GB at 8K and 16.6 GB at 32K.

Where can I download Gemma3_27B GGUF?

The files are on Hugging Face in the sleeping-ai/Gemma3-27B-IT-TQ2-0 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Gemma3_27B use?

Hugging Face lists the license as mit. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Other GGUFs of gemma-3-27b-it

Similar models

Browse all →

More from sleeping-ai

All by sleeping-ai →

More Gemma models

All Gemma →

Other medium models

All medium models →