Instructions to use NotRIK/auri-v3-qwen with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use NotRIK/auri-v3-qwen 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 NotRIK/auri-v3-qwen:Q4_0
# Run inference directly in the terminal:
llama cli -hf NotRIK/auri-v3-qwen:Q4_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf NotRIK/auri-v3-qwen:Q4_0
# Run inference directly in the terminal:
llama cli -hf NotRIK/auri-v3-qwen:Q4_0

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf NotRIK/auri-v3-qwen:Q4_0
# Run inference directly in the terminal:
./build/bin/llama cli -hf NotRIK/auri-v3-qwen:Q4_0

Use Docker

docker model run hf.co/NotRIK/auri-v3-qwen:Q4_0

Llama new
LM Studio
Jan
Ollama
How to use NotRIK/auri-v3-qwen with Ollama:
```
ollama run hf.co/NotRIK/auri-v3-qwen:Q4_0
```
Unsloth Desktop

How to use NotRIK/auri-v3-qwen with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf NotRIK/auri-v3-qwen:Q4_0

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": "NotRIK/auri-v3-qwen:Q4_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use NotRIK/auri-v3-qwen with Docker Model Runner:
```
docker model run hf.co/NotRIK/auri-v3-qwen:Q4_0
```

Lemonade

How to use NotRIK/auri-v3-qwen with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull NotRIK/auri-v3-qwen:Q4_0

Run and chat with the model

lemonade run user.auri-v3-qwen-Q4_0

List all available models

lemonade list

Hermes Agent

How to use NotRIK/auri-v3-qwen with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf NotRIK/auri-v3-qwen:Q4_0

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 NotRIK/auri-v3-qwen:Q4_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use NotRIK/auri-v3-qwen with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf NotRIK/auri-v3-qwen:Q4_0

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 "NotRIK/auri-v3-qwen:Q4_0" \
  --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"

✨ Auri V3 — On-Device Multilingual Android Screen Agent

Created by: Not Rik

Auri V3 is a lightweight, high-intelligence Android screen-control AI agent fine-tuned from Qwen3.5-2B. It is optimized for on-device mobile execution (arm64-v8a) via llama.cpp.

Key Capabilities:

Multilingual Command & Narration: Fluent Bengali (বাংলা), Hindi (हिन्दी), Hinglish, and English.
Android Screen Navigation: Tool calling (tap_node, type_text, open_app, open_url, swipe, system_nav).
Autonomous Auto-Chat Standby Mode: Contextual on-screen replies while protecting against sensitive financial/UPI requests.
Device & Web Tools: Live web search, device status (battery/storage), flashlight, and alarm settings.
Safety Gate: User confirmation protocol before executing calls, installs, or messages.

Files in this Repository:

auri_v3_qwen_q4_k_m.gguf: Recommended format for high reasoning precision (~1.4 GB).
auri_v3_qwen_q4_0.gguf: Ultra-fast ARM64 SIMD format (~1.2 GB).
auri_v3_qwen_mmproj.gguf: Multimodal vision projector for image & canvas analysis.