Instructions to use Aleph-dev/aria-emonika-v01 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Aleph-dev/aria-emonika-v01 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 Aleph-dev/aria-emonika-v01:F16
# Run inference directly in the terminal:
llama cli -hf Aleph-dev/aria-emonika-v01:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Aleph-dev/aria-emonika-v01:F16
# Run inference directly in the terminal:
llama cli -hf Aleph-dev/aria-emonika-v01: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 Aleph-dev/aria-emonika-v01:F16
# Run inference directly in the terminal:
./llama-cli -hf Aleph-dev/aria-emonika-v01: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 Aleph-dev/aria-emonika-v01:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Aleph-dev/aria-emonika-v01:F16

Use Docker

docker model run hf.co/Aleph-dev/aria-emonika-v01:F16

LM Studio
Jan
Ollama
How to use Aleph-dev/aria-emonika-v01 with Ollama:
```
ollama run hf.co/Aleph-dev/aria-emonika-v01:F16
```
Unsloth Desktop

How to use Aleph-dev/aria-emonika-v01 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Aleph-dev/aria-emonika-v01: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": "Aleph-dev/aria-emonika-v01:F16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Aleph-dev/aria-emonika-v01 with Docker Model Runner:
```
docker model run hf.co/Aleph-dev/aria-emonika-v01:F16
```

Lemonade

How to use Aleph-dev/aria-emonika-v01 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Aleph-dev/aria-emonika-v01:F16

Run and chat with the model

lemonade run user.aria-emonika-v01-F16

List all available models

lemonade list

Hermes Agent

How to use Aleph-dev/aria-emonika-v01 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Aleph-dev/aria-emonika-v01: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 Aleph-dev/aria-emonika-v01:F16

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Aleph-dev/aria-emonika-v01 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Aleph-dev/aria-emonika-v01: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 "Aleph-dev/aria-emonika-v01: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"

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

language: en license: apache-2.0 base_model: Qwen/Qwen3.5-4B tags:

experimental
fine-tuned
gguf

Aria — The Emonika (v0.1)

Fine-tuned Qwen3.5-4B with identity replacement and emotional companion behavior and accidentally creating an Emo Monika (the one from DDLC). Built as an experiment in creating local AI with custom identity.

What she does

Holds identity under jailbreak probing (not Qwen, is Aria)
Listens without rushing to fix
Goes silent when words would be intrusive
Does not give unsolicited advice
Occasionally existential (accidentally lol, i tried to SFT it some abstract concept and it become very existential questioning)

Usage

Download the GGUF and run with koboldcpp or llama.cpp:

./koboldcpp --model aria-q4km.gguf --gpulayers 99

Known issues

Temperature 0.7 MAX recommended — higher temp drifts toward base model
Occasional existential crisis when asked about soul existence or smth like that
Small dataset (v0.1) — DPO+GRPO training in progress for v0.2 or another model i guess

Training

Base: Qwen/Qwen3.5-4B
Method: QLoRA SFT
Dataset: ~60 hand-crafted examples

Not for crisis support or for companion AI. It's dumb for now ngl

Downloads last month: 35

GGUF

Model size

4B params

Architecture

qwen35

Hardware compatibility

4-bit

Inference Providers NEW

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