GE

gemma 7b it

GemmaGGUF by googleUpdated 2024-08-14
Download on Hugging Face
Parameters8.54B
Context—
Layers—
Architecture—
Smallest quant34.2 GB
Quick answer

gemma 7b it needs about 38.8 GB of memory at its main file (a 34.2 GB file) with an 8K context window, so it fits on a 48 GB GPU.

Gemma 7B IT – 8.54B parameter language model

Gemma 7B IT is a 8.54B parameter model from Google. It is available in a GGUF format with an unknown quantization. The file size is 34.16 GB and requires approximately 38.8 GB of memory at 8 k context length.

Good at

  • Large language understanding
  • Contextual generation
  • Multilingual support

Limits

  • Unknown quantization limits memory usage
  • Requires ~38.8 GB VRAM at 8 k context
  • No vision capabilities

Best for

  • Chatbot development
  • Content drafting
  • Code generation

Who it’s for. Developers and researchers needing a large language model with a 7 B parameter count. Suitable for projects that can accommodate the memory demands of the GGUF file.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—34.2 GB 38.8 GB
Too big Get file →

The GGUF file is 34.16 GB with an estimated memory usage of 38.8 GB at 8 k context. For systems with 40 GB VRAM, use the provided quantization. If VRAM is lower, a different quantization is required, but none is listed.

What GPU do you need for gemma 7b it?

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: 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 (34.2 GB file, about 38.8 GB in use).

Specifications

Architecture from the GGUF header

Parameters8.54B

Source

Quantized bygoogle
FamilyGemma
Base modelgoogle/gemma-7b
Licensegemma
Downloads (HF)22,578
Last updated2024-08-14

Frequently asked questions about gemma 7b it

How much VRAM does gemma 7b it need?

About 38.8 GB at its main file with an 8K context window. That is the 34.2 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 7b it on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 38.8 GB, so you would need a larger GPU or CPU offloading.

What is the file size of gemma 7b it GGUF?

It depends on the quant: file is 34.2 GB.

Where can I download gemma 7b it GGUF?

The files are on Hugging Face in the google/gemma-7b-it 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 7b it 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 7B IT on 8 GB VRAM?

No, the model requires approximately 38.8 GB of VRAM at 8 k context. 8 GB is insufficient.

What quantization is available for Gemma 7B IT?

The GGUF file lists an unknown quantization. No specific quant names are provided.

Does Gemma 7B IT support vision tasks?

No, the model does not have vision capabilities.

Other GGUFs of gemma-7b

Similar models

Browse all →

More from google

All by google →

More Gemma models

All Gemma →

Other small models

All small models →