GE

gemma 2b

GemmaGGUF by googleUpdated 2024-09-27
Download on Hugging Face
Parameters2.51B
Context—
Layers—
Architecture—
Smallest quant10.0 GB
Quick answer

gemma 2b needs about 11.7 GB of memory at its main file (a 10.0 GB file) with an 8K context window, so it fits on a 12 GB GPU.

Gemma 2B – 2.51 B parameter LLM in GGUF format

Gemma 2B is a 2.51 B parameter language model released by Google. The GGUF file is 10.03 GB and requires approximately 11.7 GB of VRAM at an 8 k context length. It is available under the gemma license.

Good at

  • Large context handling
  • High parameter count
  • LLM inference

Limits

  • Requires 11.7 GB VRAM at 8 k context
  • No quantization options listed
  • License restricts commercial use

Best for

  • Research prototyping
  • Benchmarking LLMs
  • Educational demos

Who it’s for. Developers and researchers who need a large‑parameter model for testing and experimentation. The model is suitable for environments with sufficient GPU memory and compliance with the gemma license.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—10.0 GB 11.7 GB
Too big Get file →

The only available GGUF file is the 10.03 GB unquantized version. It requires about 11.7 GB VRAM at 8 k context. No smaller quantized variants are provided, so memory budget must accommodate this size.

What GPU do you need for gemma 2b?

These figures add the file size, an fp16 KV cache at an 8K context window 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 the main file (10.0 GB file, about 11.7 GB in use).

Specifications

Architecture from the GGUF header

Parameters2.51B

Source

Quantized bygoogle
FamilyGemma
Repositorygoogle/gemma-2b
Licensegemma
Downloads (HF)95,538
Last updated2024-09-27

Frequently asked questions about gemma 2b

How much VRAM does gemma 2b need?

About 11.7 GB at its main file with an 8K context window. That is the 10.0 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 2b on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 11.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of gemma 2b GGUF?

It depends on the quant: file is 10.0 GB.

Where can I download gemma 2b GGUF?

The files are on Hugging Face in the google/gemma-2b 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 2b use?

Hugging Face lists the license as gemma. 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 2B on 8 GB VRAM?

No. The model needs approximately 11.7 GB VRAM at an 8 k context length.

Is there a quantized version of Gemma 2B?

Only the unquantized 10.03 GB GGUF file is available; no other quantizations are listed.

What license applies to Gemma 2B?

The model is released under the gemma license.

Similar models

Browse all →

More from google

All by google →

More Gemma models

All Gemma →

Other tiny models

All tiny models →