Instructions to use TAOTAO777/ai-girlfriend-natsume with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TAOTAO777/ai-girlfriend-natsume with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="TAOTAO777/ai-girlfriend-natsume",
	filename="llm/Qwen3.6-35B-A3B-uncensored-heretic-APEX-I-Compact.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use TAOTAO777/ai-girlfriend-natsume with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf TAOTAO777/ai-girlfriend-natsume
# Run inference directly in the terminal:
llama-cli -hf TAOTAO777/ai-girlfriend-natsume

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf TAOTAO777/ai-girlfriend-natsume
# Run inference directly in the terminal:
llama-cli -hf TAOTAO777/ai-girlfriend-natsume

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 TAOTAO777/ai-girlfriend-natsume
# Run inference directly in the terminal:
./llama-cli -hf TAOTAO777/ai-girlfriend-natsume

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 TAOTAO777/ai-girlfriend-natsume
# Run inference directly in the terminal:
./build/bin/llama-cli -hf TAOTAO777/ai-girlfriend-natsume

Use Docker

docker model run hf.co/TAOTAO777/ai-girlfriend-natsume

LM Studio
Jan
Ollama
How to use TAOTAO777/ai-girlfriend-natsume with Ollama:
```
ollama run hf.co/TAOTAO777/ai-girlfriend-natsume
```

Unsloth Studio

How to use TAOTAO777/ai-girlfriend-natsume with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for TAOTAO777/ai-girlfriend-natsume to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for TAOTAO777/ai-girlfriend-natsume to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for TAOTAO777/ai-girlfriend-natsume to start chatting

How to use TAOTAO777/ai-girlfriend-natsume with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf TAOTAO777/ai-girlfriend-natsume

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "TAOTAO777/ai-girlfriend-natsume"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use TAOTAO777/ai-girlfriend-natsume with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf TAOTAO777/ai-girlfriend-natsume

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 TAOTAO777/ai-girlfriend-natsume

Run Hermes

hermes

Docker Model Runner
How to use TAOTAO777/ai-girlfriend-natsume with Docker Model Runner:
```
docker model run hf.co/TAOTAO777/ai-girlfriend-natsume
```

Lemonade

How to use TAOTAO777/ai-girlfriend-natsume with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull TAOTAO777/ai-girlfriend-natsume

Run and chat with the model

lemonade run user.ai-girlfriend-natsume-{{QUANT_TAG}}

List all available models

lemonade list

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

Check out the documentation for more information.

AI Girlfriend — Shiki Natsume (四季夏目) · Model Repository

This is the model distribution repository for AI Girlfriend 四季夏目.

📖 English | 中文

⚠️ Disclaimer

All model files in this repository are existing community open-source models. I am only mirroring and redistributing them for convenience. I claim no ownership over any of these models.

Original authors and licenses:

Model	Author	Source	License
Qwen3.6-35B-A3B-APEX	mudler	HuggingFace	Apache 2.0 (Qwen)
WAI-Nsfw-Illustrious-17	WAI0731	CivitAI	Community model
miaomiaoHarem_v20	miaomiao0226	CivitAI	Community model
GPT-SoVITS weights	Self-trained	—	Free to use

This project is purely non-profit and personal. No commercial use intended. If any original author objects to mirror distribution, please contact me to take it down.

Download

# Download everything
huggingface-cli download TAOTAO777/ai-girlfriend-natsume --local-dir ./models

# Or selectively:
huggingface-cli download TAOTAO777/ai-girlfriend-natsume llm/ --local-dir ./models
huggingface-cli download TAOTAO777/ai-girlfriend-natsume comfyui-checkpoints/ --local-dir ./checkpoints
huggingface-cli download TAOTAO777/ai-girlfriend-natsume gpt-sovits-weights/ --local-dir ./gpt-sovits-weights

Directory Mapping

Place downloaded files according to the source project's expected paths:

llm/
└── Qwen3.6-35B-A3B-APEX-I-Compact.gguf
    → Expected at: <your vllm>/models/

comfyui-checkpoints/
├── WAI-Nsfw-Illustrious-17.safetensors
└── miaomiaoHarem_v20.safetensors
    → Expected at: <ComfyUI>/models/checkpoints/

gpt-sovits-weights/
├── SoVITS_weights_v2Pro/xxx-e30.ckpt
└── GPT_weights_v2Pro/xxx_e20_s6240.pth
    → Expected at: <GPT-SoVITS>/SoVITS_weights_v2Pro/ and GPT_weights_v2Pro/

Main Project Repo

Source code and configuration: TAOTAO777/ai-girlfriend-natsume (GitHub)

中文章节

⚠️ 免责声明

本仓库中的模型文件均为社区开源模型，本人仅做收集和镜像分发，不声称任何所有权。本项目完全非盈利，纯个人兴趣，不涉及任何商业用途。若原作者认为镜像分发不妥，请联系我删除。

原作者列表

模型	原作者	原始来源	许可证
Qwen3.6-35B-A3B-APEX	mudler	HuggingFace	Apache 2.0 (Qwen)
WAI-Nsfw-Illustrious-17	WAI0731	CivitAI	社区模型
miaomiaoHarem_v20	miaomiao0226	CivitAI	社区模型
GPT-SoVITS 权重	本人训练	—	自由使用

下载方式

# 全量下载
huggingface-cli download TAOTAO777/ai-girlfriend-natsume --local-dir ./models

目录对应

llm/           → <你的vllm>/models/
comfyui-checkpoints/  → <ComfyUI>/models/checkpoints/
gpt-sovits-weights/   → <GPT-SoVITS>/SoVITS_weights_v2Pro/ + GPT_weights_v2Pro/

主项目

代码和配置：TAOTAO777/ai-girlfriend-natsume (GitHub)

Downloads last month: 199

GGUF

Model size

35B params

Architecture

qwen35moe

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

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