GE

gemma3 27b 20260526

GemmaGGUF by REALMS-CGUpdated 2026-05-26
Download on Hugging Face
Parameters27.4B
Context128K
Layers62
Architecturegemma3
Smallest quant17.4 GB
Quick answer

gemma3 27b 20260526 needs about 22.1 GB of memory at its main file (a 17.4 GB file) with an 8K context window, so it fits on a 24 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 16.6 GB.

gemma3 27b 20260526 is a 27.4B-parameter Gemma model in GGUF format, quantized by REALMS-CG. Its trained context length is 128K tokens. The repository has 1 quant file, from 17.4 GB to 17.4 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—17.4 GB 22.1 GB
Too big Get file →

What GPU do you need for gemma3 27b 20260526?

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: the best quant that fits is the main file (17.4 GB file, about 22.1 GB in use).

Specifications

Architecture from the GGUF header

Architecturegemma3
Parameters27.4B
Layers62
Trained context131,072 tokens
KV cache (fp16)496 KB per token

Source

Quantized byREALMS-CG
FamilyGemma
Downloads (HF)7
Last updated2026-05-26

Frequently asked questions about gemma3 27b 20260526

How much VRAM does gemma3 27b 20260526 need?

About 22.1 GB at its main file with an 8K context window. That is the 17.4 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 20260526 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 22.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of gemma3 27b 20260526 GGUF?

It depends on the quant: file is 17.4 GB.

What context length does gemma3 27b 20260526 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 20260526 GGUF?

The files are on Hugging Face in the REALMS-CG/gemma3-27b-20260526 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from REALMS-CG

All by REALMS-CG →

More Gemma models

All Gemma →

Other medium models

All medium models →