Instructions to use EryriLabs/Llama-3.2-SARA-3b-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use EryriLabs/Llama-3.2-SARA-3b-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="EryriLabs/Llama-3.2-SARA-3b-GGUF",
	filename="Llama-3.2-SARA-3b-GGUF.F16.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use EryriLabs/Llama-3.2-SARA-3b-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf EryriLabs/Llama-3.2-SARA-3b-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf EryriLabs/Llama-3.2-SARA-3b-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf EryriLabs/Llama-3.2-SARA-3b-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf EryriLabs/Llama-3.2-SARA-3b-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf EryriLabs/Llama-3.2-SARA-3b-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf EryriLabs/Llama-3.2-SARA-3b-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf EryriLabs/Llama-3.2-SARA-3b-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf EryriLabs/Llama-3.2-SARA-3b-GGUF:Q4_K_M

Use Docker

docker model run hf.co/EryriLabs/Llama-3.2-SARA-3b-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use EryriLabs/Llama-3.2-SARA-3b-GGUF with Ollama:
```
ollama run hf.co/EryriLabs/Llama-3.2-SARA-3b-GGUF:Q4_K_M
```

Unsloth Studio

How to use EryriLabs/Llama-3.2-SARA-3b-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for EryriLabs/Llama-3.2-SARA-3b-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for EryriLabs/Llama-3.2-SARA-3b-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for EryriLabs/Llama-3.2-SARA-3b-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use EryriLabs/Llama-3.2-SARA-3b-GGUF with Docker Model Runner:
```
docker model run hf.co/EryriLabs/Llama-3.2-SARA-3b-GGUF:Q4_K_M
```

Lemonade

How to use EryriLabs/Llama-3.2-SARA-3b-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull EryriLabs/Llama-3.2-SARA-3b-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Llama-3.2-SARA-3b-GGUF-Q4_K_M

List all available models

lemonade list

Model Card for `EryriLabs/Llama-3.2-SARA-3b-GGUF`

This model is a GGUF-quantized version of EryriLabs/Llama-3.2-SARA-3b, designed for efficient, low-memory usage on resource-constrained devices. SARA (Security Awareness and Resilience Assistant) provides practical, conversational cybersecurity advice in an offline-friendly format.

Model Details

Base Model: unsloth/Llama-3.2-3B-GGUF
Quantization: GGUF
Language: English (en)
License: llama3.2
Developer: EryriLabs

Intended Use

This model is optimized for offline, low-spec hardware environments, serving as a lightweight assistant for basic cybersecurity guidance in English. It was trained as part of an ongoing blog series (https://www.eryrilabs.co.uk/post/building-sara-a-lightweight-cybersecurity-assistant-for-everyday-laptops).

Ollama Modelfile

FROM Llama-3.2-SARA-3b-GGUF.F16.gguf PARAMETER temperature 0.4 PARAMETER stop "<|im_start|>" PARAMETER stop "<|im_end|>" TEMPLATE """ <|im_start|>system {{ .System }}<|im_end|> <|im_start|>user {{ .Prompt }}<|im_end|> <|im_start|>assistant """ SYSTEM """You are a helpful assistant."""

Limitations

Designed for general guidance only; not suitable for advanced or professional cybersecurity consultation.

Downloads last month: 17

GGUF

Model size

4B params

Architecture

llama

Hardware compatibility

4-bit

8-bit

16-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for EryriLabs/Llama-3.2-SARA-3b-GGUF

Base model

meta-llama/Llama-3.2-3B

Quantized

unsloth/Llama-3.2-3B-bnb-4bit

Finetuned

EryriLabs/Llama-3.2-SARA-3b