Instructions to use mia1312/mia-files with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use mia1312/mia-files 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 mia1312/mia-files:Q4_0
# Run inference directly in the terminal:
llama cli -hf mia1312/mia-files:Q4_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf mia1312/mia-files:Q4_0
# Run inference directly in the terminal:
llama cli -hf mia1312/mia-files: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 mia1312/mia-files:Q4_0
# Run inference directly in the terminal:
./build/bin/llama cli -hf mia1312/mia-files:Q4_0

Use Docker

docker model run hf.co/mia1312/mia-files:Q4_0

Llama new
LM Studio
Jan
Ollama
How to use mia1312/mia-files with Ollama:
```
ollama run hf.co/mia1312/mia-files:Q4_0
```
Unsloth Desktop

How to use mia1312/mia-files with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf mia1312/mia-files: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": "mia1312/mia-files:Q4_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use mia1312/mia-files with Docker Model Runner:
```
docker model run hf.co/mia1312/mia-files:Q4_0
```

Lemonade

How to use mia1312/mia-files with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mia1312/mia-files:Q4_0

Run and chat with the model

lemonade run user.mia-files-Q4_0

List all available models

lemonade list

Hermes Agent

How to use mia1312/mia-files with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf mia1312/mia-files: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 mia1312/mia-files:Q4_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use mia1312/mia-files with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf mia1312/mia-files: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 "mia1312/mia-files: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"

Mia files

The files the Mia - AI Companion Android app downloads on first start, mirrored here so the app's downloads keep working.

File	What it is	Original source	License
`Qwen3.5-0.8B-Q4_0.gguf`	Language model for phones with 4 GB of memory	unsloth/Qwen3.5-0.8B-GGUF, from Qwen	Apache 2.0 (`LICENSE-Qwen3.5`)
`Qwen3.5-2B-Q4_0.gguf`	Language model for other phones	unsloth/Qwen3.5-2B-GGUF, from Qwen	Apache 2.0 (`LICENSE-Qwen3.5`)
`voice/`	Supertonic 3 text-to-speech, int8 for sherpa-onnx	csukuangfj2/sherpa-onnx-supertonic-3-tts-int8-2026-05-11, from Supertone Inc.	OpenRAIL-M (`voice/LICENSE`)

The files are unchanged copies. The voice models may not be used to break the law, harm or exploit minors, harass, defame or impersonate people, spread disinformation, or give medical advice without supervision (see voice/LICENSE).

Downloads last month: 17

GGUF

Model size

0.8B params

Architecture

qwen35

Hardware compatibility

4-bit

Inference Providers NEW

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