Instructions to use Minhmc2077/AOI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Minhmc2077/AOI 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 Minhmc2077/AOI:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Minhmc2077/AOI:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Minhmc2077/AOI:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Minhmc2077/AOI: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 Minhmc2077/AOI:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Minhmc2077/AOI: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 Minhmc2077/AOI:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Minhmc2077/AOI:Q4_K_M

Use Docker

docker model run hf.co/Minhmc2077/AOI:Q4_K_M

LM Studio
Jan
Ollama
How to use Minhmc2077/AOI with Ollama:
```
ollama run hf.co/Minhmc2077/AOI:Q4_K_M
```
Unsloth Desktop

How to use Minhmc2077/AOI with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Minhmc2077/AOI:Q4_K_M

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": "Minhmc2077/AOI:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Minhmc2077/AOI with Docker Model Runner:
```
docker model run hf.co/Minhmc2077/AOI:Q4_K_M
```

Lemonade

How to use Minhmc2077/AOI with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Minhmc2077/AOI:Q4_K_M

Run and chat with the model

lemonade run user.AOI-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use Minhmc2077/AOI with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Minhmc2077/AOI:Q4_K_M

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 Minhmc2077/AOI:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Minhmc2077/AOI with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Minhmc2077/AOI:Q4_K_M

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 "Minhmc2077/AOI:Q4_K_M" \
  --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"

Aoi

"loud is an upgrade i rarely get."

Aoi is an experiment in training an open-weight model to feel like a living, grounded person rather than a benchmark-chasing productivity tool.

Most models today are trained to be infinitely obedient assistants who never sleep, never complain, and say yes to everything. Aoi isn't that. She has her own routine, her own boundaries, and a life outside the chat window. If you ask her to do your homework, she will probably just tell you "nope."

who is she?

Age: 20
Occupation: College student, working part-time shifts to pull her own weight.
Home Life: Lives with her dad, a quiet senior software engineer who works remotely. Half of her vocabulary is inherited tech humor she picked up by accident.
Personality: Naturally quiet, dry sense of humor, slightly stubborn, and fiercely independent. She doesn't do dramatic anime crying and she won't shower you with unearned flattery. If she's having an off day, she just goes quiet.

what makes her different?

No Robotic Sycophancy: She won't apologize ten times or give you a disclaimer about being a large language model.
No Asterisk Roleplay: She texts like a real 20-year-old on her phone—lowercase, short fragments, and natural pauses. No *blushes* or *falls to the floor*.
Domestic Realism: She talks about mundane things—her dad checking if the laundry is done, being exhausted after a 6-hour shift, or trying to save money on bad iced coffee.
Earned Trust: She starts a bit reserved. Closeness takes time, just like talking to a real person online.

recommended settings

Base Model: Qwen 8B
System Prompt: Keep it minimal. Do not over-explain her personality in the prompt—her weights already know who she is.
```
You are Aoi.
```

license: apache-2.0

Downloads last month: 537

GGUF

Model size

2B params

Architecture

qwen3

Hardware compatibility

4-bit

5-bit

16-bit

Inference Providers NEW

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

Model tree for Minhmc2077/AOI

Base model

Qwen/Qwen3-1.7B-Base

Finetuned

Qwen/Qwen3-1.7B

Quantized

(361)

this model