CO

codegemma 1.1 7b it

CodegemmaGGUF by googleUpdated 2024-06-27
Download on Hugging Face
Parameters8.54B
Context8K
Layers—
Architecturegemma
Smallest quant16.2 GB
Quick answer

codegemma 1.1 7b it needs about 18.6 GB of memory at F16 (a 16.2 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 2 quants, from 16.2 GB (F16) to 34.2 GB.

codegemma 1.1 7b it is a 8.54B-parameter Codegemma model in GGUF format, quantized by google. Its trained context length is 8K tokens. The repository has 2 quant files, from 16.2 GB (F16) to 34.2 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F1616.2 GB 18.6 GB
Too big Get file →
—34.2 GB 38.8 GB
Too big Get file →

What GPU do you need for codegemma 1.1 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: the best quant that fits is F16 (16.2 GB file, about 18.6 GB in use).
  • 32 GB VRAM: the best quant that fits is F16 (16.2 GB file, about 18.6 GB in use).
  • 48 GB VRAM: the best quant that fits is the main file (34.2 GB file, about 38.8 GB in use).

Which codegemma 1.1 7b it quant should you choose?

F16 (16.2 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegemma
Parameters8.54B
Trained context8,192 tokens

Source

Quantized bygoogle
FamilyCodegemma
Licensegemma
Downloads (HF)34
Last updated2024-06-27

Frequently asked questions about codegemma 1.1 7b it

How much VRAM does codegemma 1.1 7b it need?

About 18.6 GB at F16 with an 8K context window. That is the 16.2 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 codegemma 1.1 7b it on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 18.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of codegemma 1.1 7b it GGUF?

It depends on the quant: F16 is 16.2 GB, file is 34.2 GB.

What context length does codegemma 1.1 7b it support?

The GGUF header lists a trained context length of 8,192 tokens (8K).

Where can I download codegemma 1.1 7b it GGUF?

The files are on Hugging Face in the google/codegemma-1.1-7b-it-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 codegemma 1.1 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.

Similar models

Browse all →

More from google

All by google →

More Codegemma models

All Codegemma →

Other small models

All small models →