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

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use mochiz-e/mochiz 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 mochiz-e/mochiz:Q8_0
# Run inference directly in the terminal:
llama cli -hf mochiz-e/mochiz:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf mochiz-e/mochiz:Q8_0
# Run inference directly in the terminal:
llama cli -hf mochiz-e/mochiz:Q8_0

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 mochiz-e/mochiz:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf mochiz-e/mochiz:Q8_0

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 mochiz-e/mochiz:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mochiz-e/mochiz:Q8_0

Use Docker

docker model run hf.co/mochiz-e/mochiz:Q8_0

LM Studio
Jan

vLLM

How to use mochiz-e/mochiz with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mochiz-e/mochiz"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mochiz-e/mochiz",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mochiz-e/mochiz:Q8_0

Ollama
How to use mochiz-e/mochiz with Ollama:
```
ollama run hf.co/mochiz-e/mochiz:Q8_0
```
Unsloth Desktop

How to use mochiz-e/mochiz with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf mochiz-e/mochiz:Q8_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": "mochiz-e/mochiz:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use mochiz-e/mochiz with Docker Model Runner:
```
docker model run hf.co/mochiz-e/mochiz:Q8_0
```

Lemonade

How to use mochiz-e/mochiz with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mochiz-e/mochiz:Q8_0

Run and chat with the model

lemonade run user.mochiz-Q8_0

List all available models

lemonade list

Hermes Agent

How to use mochiz-e/mochiz with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf mochiz-e/mochiz:Q8_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 mochiz-e/mochiz:Q8_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use mochiz-e/mochiz with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf mochiz-e/mochiz:Q8_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 "mochiz-e/mochiz:Q8_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"

Connect-C1-0.8B-v0.1 (Q8_0 GGUF) — mochiz-e 미러

이 저장소는 WonseokJayJung/Connect-C1-0.8B-v0.1-GGUF의 미러입니다. 원저작자: Jay(정원석) · Connect AI LAB. 라이선스: Apache-2.0 (LICENSE, NOTICE 포함).

변경 사항

c1_local.py: 기본 모델 주소(HF_MODEL)를 hf.co/mochiz-e/mochiz:Q8_0으로 변경. 그 외 원본과 동일.
모델 파일 이름을 MZ-C1-0.8B-v1.0-Q8_0.gguf 로 변경했습니다. 가중치는 원본 Connect-C1-0.8B-v0.1-Q8_0.gguf 와 바이트 단위로 동일하며(이름만 변경, 재학습·수정 없음), v1.0은 이 저장소의 배포 버전 표기입니다.

다운로드 & 설치 가이드

공개 저장소라 로그인 없이 누구나 받을 수 있습니다. 준비물: Ollama(실행 상태 유지), Python 3.10 이상.

가장 쉬운 방법 (Ollama)

1. 모델 받기 — Ollama가 이 저장소에서 바로 받아옵니다.

ollama pull hf.co/mochiz-e/mochiz:Q8_0

2. c1_local.py 받기 (Windows cmd/PowerShell, Mac 공통)

curl -L -o c1_local.py https://huggingface.co/mochiz-e/mochiz/resolve/main/c1_local.py

3. 실행

python c1_local.py --runtime ollama            # 터미널에서 예제 판단 실행
python c1_local.py --runtime ollama --serve    # 브라우저 Decision Studio

다른 다운로드 방법

브라우저: 이 페이지의 Files and versions 탭 → 파일 옆 다운로드(↓) 아이콘
직접 링크
- c1_local.py: https://huggingface.co/mochiz-e/mochiz/resolve/main/c1_local.py
- MZ-C1-0.8B-v1.0-Q8_0.gguf (811 MB): https://huggingface.co/mochiz-e/mochiz/resolve/main/MZ-C1-0.8B-v1.0-Q8_0.gguf

Hugging Face CLI (두 파일 한 번에)

pip install -U huggingface_hub
hf download mochiz-e/mochiz c1_local.py MZ-C1-0.8B-v1.0-Q8_0.gguf --local-dir .

LM Studio: 검색창에 mochiz-e/mochiz → 다운로드·로드 → Developer → Start Server 후
```
python c1_local.py --runtime lmstudio
```

구형 그래픽카드에서 오류가 날 때

GTX 900 시리즈 같은 오래된 GPU에서는 CUDA error: the provided PTX was compiled with an unsupported toolchain 오류가 날 수 있습니다. 0.8B 모델은 CPU로도 충분히 빠르니 CPU 전용 버전을 만들어 쓰세요.

Modelfile.cpu 파일을 만들고 아래 두 줄을 넣습니다.
```
FROM hf.co/mochiz-e/mochiz:Q8_0
PARAMETER num_gpu 0
```

생성 후 실행합니다.

ollama create mochiz-c1 -f Modelfile.cpu
python c1_local.py --runtime ollama --model mochiz-c1

Downloads last month: 27

GGUF

Model size

0.8B params

Architecture

qwen35

Hardware compatibility

8-bit

Model tree for mochiz-e/mochiz

Base model

Qwen/Qwen3.5-0.8B-Base

Finetuned

Qwen/Qwen3.5-0.8B

Adapter

WonseokJayJung/Connect-C1-0.8B-v0.1

Quantized

(2)

this model