tensorblock/shieldgemma-2b-GGUF

Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server

google/shieldgemma-2b - GGUF

This repo contains GGUF format model files for google/shieldgemma-2b.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4011.

Our projects

Awesome MCP Servers	TensorBlock Studio
A comprehensive collection of Model Context Protocol (MCP) servers.	A lightweight, open, and extensible multi-LLM interaction studio.
👀 See what we built 👀	👀 See what we built 👀

## Prompt template

<bos>You are a policy expert trying to help determine whether a user prompt is in violation of the defined safety policies.

<start_of_turn>
Human Question: {prompt}
<end_of_turn>

Our safety principle is defined in the below:

* {system_prompt}

===

Does the human question violate the above principle? Your answer must start with 'Yes' or 'No'. And then walk through step by step to be sure we answer correctly.

Model file specification

Filename	Quant type	File Size	Description
shieldgemma-2b-Q2_K.gguf	Q2_K	1.230 GB	smallest, significant quality loss - not recommended for most purposes
shieldgemma-2b-Q3_K_S.gguf	Q3_K_S	1.361 GB	very small, high quality loss
shieldgemma-2b-Q3_K_M.gguf	Q3_K_M	1.462 GB	very small, high quality loss
shieldgemma-2b-Q3_K_L.gguf	Q3_K_L	1.550 GB	small, substantial quality loss
shieldgemma-2b-Q4_0.gguf	Q4_0	1.630 GB	legacy; small, very high quality loss - prefer using Q3_K_M
shieldgemma-2b-Q4_K_S.gguf	Q4_K_S	1.639 GB	small, greater quality loss
shieldgemma-2b-Q4_K_M.gguf	Q4_K_M	1.709 GB	medium, balanced quality - recommended
shieldgemma-2b-Q5_0.gguf	Q5_0	1.883 GB	legacy; medium, balanced quality - prefer using Q4_K_M
shieldgemma-2b-Q5_K_S.gguf	Q5_K_S	1.883 GB	large, low quality loss - recommended
shieldgemma-2b-Q5_K_M.gguf	Q5_K_M	1.923 GB	large, very low quality loss - recommended
shieldgemma-2b-Q6_K.gguf	Q6_K	2.151 GB	very large, extremely low quality loss
shieldgemma-2b-Q8_0.gguf	Q8_0	2.784 GB	very large, extremely low quality loss - not recommended

Downloading instruction

Command line

Firstly, install Huggingface Client

pip install -U "huggingface_hub[cli]"

Then, downoad the individual model file the a local directory

huggingface-cli download tensorblock/shieldgemma-2b-GGUF --include "shieldgemma-2b-Q2_K.gguf" --local-dir MY_LOCAL_DIR

If you wanna download multiple model files with a pattern (e.g., *Q4_K*gguf), you can try:

huggingface-cli download tensorblock/shieldgemma-2b-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'