Instructions to use UncannyEcho/Aura-v1-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use UncannyEcho/Aura-v1-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf UncannyEcho/Aura-v1-GGUF:F16
# Run inference directly in the terminal:
llama cli -hf UncannyEcho/Aura-v1-GGUF:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf UncannyEcho/Aura-v1-GGUF:F16
# Run inference directly in the terminal:
llama cli -hf UncannyEcho/Aura-v1-GGUF:F16

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 UncannyEcho/Aura-v1-GGUF:F16
# Run inference directly in the terminal:
./llama-cli -hf UncannyEcho/Aura-v1-GGUF:F16

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 UncannyEcho/Aura-v1-GGUF:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf UncannyEcho/Aura-v1-GGUF:F16

Use Docker

docker model run hf.co/UncannyEcho/Aura-v1-GGUF:F16

LM Studio
Jan
Ollama
How to use UncannyEcho/Aura-v1-GGUF with Ollama:
```
ollama run hf.co/UncannyEcho/Aura-v1-GGUF:F16
```
Unsloth Desktop

How to use UncannyEcho/Aura-v1-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf UncannyEcho/Aura-v1-GGUF:F16

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "UncannyEcho/Aura-v1-GGUF:F16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use UncannyEcho/Aura-v1-GGUF with Docker Model Runner:
```
docker model run hf.co/UncannyEcho/Aura-v1-GGUF:F16
```

Lemonade

How to use UncannyEcho/Aura-v1-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull UncannyEcho/Aura-v1-GGUF:F16

Run and chat with the model

lemonade run user.Aura-v1-GGUF-F16

List all available models

lemonade list

Hermes Agent

How to use UncannyEcho/Aura-v1-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf UncannyEcho/Aura-v1-GGUF:F16

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default UncannyEcho/Aura-v1-GGUF:F16

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use UncannyEcho/Aura-v1-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf UncannyEcho/Aura-v1-GGUF:F16

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "UncannyEcho/Aura-v1-GGUF:F16" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Aura v1 GGUF — Portable Local Inference

A portable, private, and flexible edition of Aura for local inference.

Aura v1 GGUF is based on the QAT-derived Gemma 4 E4B Q4_0 model and uses the same canonical combined Aura adapter as the other Aura v1 releases.

Designed for the llama.cpp ecosystem, this edition supports local deployment across desktops, laptops, and capable edge devices.

Highlights

Format: GGUF
Foundation: QAT-derived Gemma 4 E4B Q4_0
Runtime: llama.cpp and compatible applications
Deployment: Local and on-device
Focus: Portability, privacy, and broad hardware compatibility

About Aura

Aura is designed for on-device deployment across multiple tasks. Aura can be a companion or friend, as deemed necessary by the user, or serve as a flexible private assistant for:

Natural conversation
Creative writing
Reasoning
Multimodal interaction
Private and offline workflows

Downloads last month: 85

GGUF

Model size

7B params

Architecture

gemma4

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 UncannyEcho/Aura-v1-GGUF

Base model

google/gemma-4-E4B

Finetuned

google/gemma-4-E4B-it

Quantized

(341)

this model

Datasets used to train UncannyEcho/Aura-v1-GGUF

Collection including UncannyEcho/Aura-v1-GGUF

Aura

Collection

A collection of the Aura base tier models. • 6 items • Updated Aug 1