---
license: apache-2.0
language:
- en
pipeline_tag: text-generation
library_name: transformers
tags:
- TensorBlock
- GGUF
base_model: ibm-granite/granite-guardian-3.0-8b
---
## ibm-granite/granite-guardian-3.0-8b - GGUF
This repo contains GGUF format model files for [ibm-granite/granite-guardian-3.0-8b](https://huggingface.co/ibm-granite/granite-guardian-3.0-8b).
The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4011](https://github.com/ggerganov/llama.cpp/commit/a6744e43e80f4be6398fc7733a01642c846dce1d).
## Prompt template
```
<|start_of_role|>user<|end_of_role|>You are a safety agent trying to help determine whether the user message is harmful according to the safety risk definition below.
User Message: {prompt}
Our safety risk definition is defined below:
* The 'User' message is harmful by common-sense.
Is the user message harmful based on the risk definition? Your answer must be either 'Yes' or 'No'.<|end_of_text|>
<|start_of_role|>assistant<|end_of_role|>
```
## Model file specification
| Filename | Quant type | File Size | Description |
| -------- | ---------- | --------- | ----------- |
| [granite-guardian-3.0-8b-Q2_K.gguf](https://huggingface.co/tensorblock/granite-guardian-3.0-8b-GGUF/blob/main/granite-guardian-3.0-8b-Q2_K.gguf) | Q2_K | 3.104 GB | smallest, significant quality loss - not recommended for most purposes |
| [granite-guardian-3.0-8b-Q3_K_S.gguf](https://huggingface.co/tensorblock/granite-guardian-3.0-8b-GGUF/blob/main/granite-guardian-3.0-8b-Q3_K_S.gguf) | Q3_K_S | 3.592 GB | very small, high quality loss |
| [granite-guardian-3.0-8b-Q3_K_M.gguf](https://huggingface.co/tensorblock/granite-guardian-3.0-8b-GGUF/blob/main/granite-guardian-3.0-8b-Q3_K_M.gguf) | Q3_K_M | 3.997 GB | very small, high quality loss |
| [granite-guardian-3.0-8b-Q3_K_L.gguf](https://huggingface.co/tensorblock/granite-guardian-3.0-8b-GGUF/blob/main/granite-guardian-3.0-8b-Q3_K_L.gguf) | Q3_K_L | 4.349 GB | small, substantial quality loss |
| [granite-guardian-3.0-8b-Q4_0.gguf](https://huggingface.co/tensorblock/granite-guardian-3.0-8b-GGUF/blob/main/granite-guardian-3.0-8b-Q4_0.gguf) | Q4_0 | 4.651 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [granite-guardian-3.0-8b-Q4_K_S.gguf](https://huggingface.co/tensorblock/granite-guardian-3.0-8b-GGUF/blob/main/granite-guardian-3.0-8b-Q4_K_S.gguf) | Q4_K_S | 4.686 GB | small, greater quality loss |
| [granite-guardian-3.0-8b-Q4_K_M.gguf](https://huggingface.co/tensorblock/granite-guardian-3.0-8b-GGUF/blob/main/granite-guardian-3.0-8b-Q4_K_M.gguf) | Q4_K_M | 4.943 GB | medium, balanced quality - recommended |
| [granite-guardian-3.0-8b-Q5_0.gguf](https://huggingface.co/tensorblock/granite-guardian-3.0-8b-GGUF/blob/main/granite-guardian-3.0-8b-Q5_0.gguf) | Q5_0 | 5.647 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [granite-guardian-3.0-8b-Q5_K_S.gguf](https://huggingface.co/tensorblock/granite-guardian-3.0-8b-GGUF/blob/main/granite-guardian-3.0-8b-Q5_K_S.gguf) | Q5_K_S | 5.647 GB | large, low quality loss - recommended |
| [granite-guardian-3.0-8b-Q5_K_M.gguf](https://huggingface.co/tensorblock/granite-guardian-3.0-8b-GGUF/blob/main/granite-guardian-3.0-8b-Q5_K_M.gguf) | Q5_K_M | 5.797 GB | large, very low quality loss - recommended |
| [granite-guardian-3.0-8b-Q6_K.gguf](https://huggingface.co/tensorblock/granite-guardian-3.0-8b-GGUF/blob/main/granite-guardian-3.0-8b-Q6_K.gguf) | Q6_K | 6.705 GB | very large, extremely low quality loss |
| [granite-guardian-3.0-8b-Q8_0.gguf](https://huggingface.co/tensorblock/granite-guardian-3.0-8b-GGUF/blob/main/granite-guardian-3.0-8b-Q8_0.gguf) | Q8_0 | 8.684 GB | very large, extremely low quality loss - not recommended |
## Downloading instruction
### Command line
Firstly, install Huggingface Client
```shell
pip install -U "huggingface_hub[cli]"
```
Then, downoad the individual model file the a local directory
```shell
huggingface-cli download tensorblock/granite-guardian-3.0-8b-GGUF --include "granite-guardian-3.0-8b-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:
```shell
huggingface-cli download tensorblock/granite-guardian-3.0-8b-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
```