GO

google shieldgemma 9b

GoogleGGUF by RichardErkhovUpdated 2024-08-23
Download on Hugging Face
Parameters9.24B
Context8K
Layers—
Architecturegemma2
Smallest quant3.1 GB
Quick answer

google shieldgemma 9b needs about 4.0 GB of memory at Q4_K_M (a 3.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 22 quants, from 3.1 GB (Q4_K_M) to 9.8 GB (Q8_0).

google shieldgemma 9b is a 9.24B-parameter Google model in GGUF format, quantized by RichardErkhov. Its trained context length is 8K tokens. The repository has 22 quant files, from 3.1 GB (Q4_K_M) to 9.8 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M3.1 GB 4.0 GB
Fits Get file →
Q2_K3.8 GB 4.8 GB
Fits Get file →
Q5_K4.1 GB 5.1 GB
Fits Get file →
IQ3_XS4.1 GB 5.1 GB
Fits Get file →
IQ3_S4.3 GB 5.4 GB
Fits Get file →
Q3_K_S4.3 GB 5.4 GB
Fits Get file →
IQ3_M4.5 GB 5.5 GB
Fits Get file →
Q3_K4.8 GB 5.8 GB
Fits Get file →
Q3_K_M4.8 GB 5.8 GB
Fits Get file →
Q3_K_L5.1 GB 6.2 GB
Fits Get file →
IQ4_XS5.2 GB 6.3 GB
Fits Get file →
Q4_05.4 GB 6.6 GB
Fits Get file →
IQ4_NL5.5 GB 6.6 GB
Fits Get file →
Q4_K_S5.5 GB 6.6 GB
Fits Get file →
Q4_K5.8 GB 7.0 GB
Fits Get file →
Q4_16.0 GB 7.2 GB
Fits Get file →
Q5_06.5 GB 7.8 GB
Tight Get file →
Q5_K_S6.5 GB 7.8 GB
Tight Get file →
Q5_K_M6.6 GB 7.9 GB
Tight Get file →
Q5_17.0 GB 8.3 GB
Too big Get file →
Q6_K7.6 GB 9.0 GB
Too big Get file →
Q8_09.8 GB 11.5 GB
Too big Get file →

What GPU do you need for google shieldgemma 9b?

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: the best quant that fits is Q4_K_M (3.1 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q3_K (4.8 GB file, about 5.8 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_M (6.6 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (9.8 GB file, about 11.5 GB in use).

Which google shieldgemma 9b quant should you choose?

Q4_K_M is the usual starting point for google shieldgemma 9b: it balances file size and quality well. Here it is a 3.1 GB file.

The Q8_0 file is 9.8 GB, about 3.2 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegemma2
Parameters9.24B
Trained context8,192 tokens

Source

Quantized byRichardErkhov
FamilyGoogle
Downloads (HF)564
Last updated2024-08-23

Frequently asked questions about google shieldgemma 9b

How much VRAM does google shieldgemma 9b need?

About 4.0 GB at Q4_K_M with an 8K context window. That is the 3.1 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 google shieldgemma 9b on an 8 GB GPU?

Yes, with Q5_K_M: the 6.6 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 google shieldgemma 9b GGUF?

It depends on the quant: Q4_K_M is 3.1 GB, Q2_K is 3.8 GB, Q5_K is 4.1 GB, IQ3_XS is 4.1 GB, IQ3_S is 4.3 GB, Q3_K_S is 4.3 GB and 16 more.

What context length does google shieldgemma 9b support?

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

Where can I download google shieldgemma 9b GGUF?

The files are on Hugging Face in the RichardErkhov/google_-_shieldgemma-9b-gguf 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 RichardErkhov

All by RichardErkhov →

More Google models

All Google →

Other small models

All small models →