GE

gemma-7b-it

GemmaGGUF by LoneStrikerUpdated 2024-03-01
Download on Hugging Face
Parameters8.54B
Context8K
Layers28
Architecturegemma
Smallest quant3.7 GB
Quick answer

gemma-7b-it needs about 9.6 GB of memory at Q4_K_M (a 5.3 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 9 quants, from 3.7 GB (Q3_K_S) to 9.1 GB (Q8_0).

gemma-7b-it is a 8.54B-parameter Gemma model in GGUF format, quantized by LoneStriker. Its trained context length is 8K tokens. The repository has 9 quant files, from 3.7 GB (Q3_K_S) to 9.1 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_S3.7 GB 7.9 GB
Tight Get file →
Q3_K_M4.1 GB 8.3 GB
Too big Get file →
Q3_K_L4.7 GB 9.0 GB
Too big Get file →
Q4_K_S4.8 GB 9.1 GB
Too big Get file →
Q4_K_M5.3 GB 9.6 GB
Too big Get file →
Q5_K_S5.9 GB 10.1 GB
Too big Get file →
Q5_K_M6.1 GB 10.4 GB
Too big Get file →
Q6_K7.0 GB 11.3 GB
Too big Get file →
Q8_09.1 GB 13.3 GB
Too big Get file →

What GPU do you need for gemma-7b-it?

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: the best quant that fits is Q3_K_S (3.7 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (7.0 GB file, about 11.3 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (9.1 GB file, about 13.3 GB in use).

Which gemma-7b-it quant should you choose?

Q4_K_M is the usual starting point for gemma-7b-it: it balances file size and quality well. Here it is a 5.3 GB file.

The Q8_0 file is 9.1 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q3_K_S at 3.7 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegemma
Parameters8.54B
Layers28
Trained context8,192 tokens
KV cache (fp16)448 KB per token

Source

Quantized byLoneStriker
FamilyGemma
Licenseother
Downloads (HF)163
Last updated2024-03-01

Frequently asked questions about gemma-7b-it

How much VRAM does gemma-7b-it need?

About 9.6 GB at Q4_K_M with an 8K context window. That is the 5.3 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?

Yes, with Q3_K_S: the 3.7 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

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

It depends on the quant: Q3_K_S is 3.7 GB, Q3_K_M is 4.1 GB, Q3_K_L is 4.7 GB, Q4_K_S is 4.8 GB, Q4_K_M is 5.3 GB, Q5_K_S is 5.9 GB and 3 more.

What context length does gemma-7b-it support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 3.8 GB at 8K and 3.8 GB at 8K.

Where can I download gemma-7b-it GGUF?

The files are on Hugging Face in the LoneStriker/gemma-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 gemma-7b-it use?

Hugging Face lists the license as other. 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 LoneStriker

All by LoneStriker →

More Gemma models

All Gemma →

Other small models

All small models →