Instructions to use AEmotionStudio/ComfyUI-Model-Backups with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AEmotionStudio/ComfyUI-Model-Backups with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="AEmotionStudio/ComfyUI-Model-Backups",
	filename="clip/Qwen2.5-VL-7B-Instruct-abliterated.Q8_0.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 AEmotionStudio/ComfyUI-Model-Backups with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf AEmotionStudio/ComfyUI-Model-Backups:Q4_K_S
# Run inference directly in the terminal:
llama-cli -hf AEmotionStudio/ComfyUI-Model-Backups:Q4_K_S

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf AEmotionStudio/ComfyUI-Model-Backups:Q4_K_S
# Run inference directly in the terminal:
llama-cli -hf AEmotionStudio/ComfyUI-Model-Backups:Q4_K_S

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 AEmotionStudio/ComfyUI-Model-Backups:Q4_K_S
# Run inference directly in the terminal:
./llama-cli -hf AEmotionStudio/ComfyUI-Model-Backups:Q4_K_S

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 AEmotionStudio/ComfyUI-Model-Backups:Q4_K_S
# Run inference directly in the terminal:
./build/bin/llama-cli -hf AEmotionStudio/ComfyUI-Model-Backups:Q4_K_S

Use Docker

docker model run hf.co/AEmotionStudio/ComfyUI-Model-Backups:Q4_K_S

LM Studio
Jan
Ollama
How to use AEmotionStudio/ComfyUI-Model-Backups with Ollama:
```
ollama run hf.co/AEmotionStudio/ComfyUI-Model-Backups:Q4_K_S
```

Unsloth Studio

How to use AEmotionStudio/ComfyUI-Model-Backups 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 AEmotionStudio/ComfyUI-Model-Backups 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 AEmotionStudio/ComfyUI-Model-Backups to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for AEmotionStudio/ComfyUI-Model-Backups to start chatting

How to use AEmotionStudio/ComfyUI-Model-Backups with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf AEmotionStudio/ComfyUI-Model-Backups:Q4_K_S

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": "AEmotionStudio/ComfyUI-Model-Backups:Q4_K_S"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use AEmotionStudio/ComfyUI-Model-Backups with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf AEmotionStudio/ComfyUI-Model-Backups:Q4_K_S

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 AEmotionStudio/ComfyUI-Model-Backups:Q4_K_S

Run Hermes

hermes

Docker Model Runner
How to use AEmotionStudio/ComfyUI-Model-Backups with Docker Model Runner:
```
docker model run hf.co/AEmotionStudio/ComfyUI-Model-Backups:Q4_K_S
```

Lemonade

How to use AEmotionStudio/ComfyUI-Model-Backups with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull AEmotionStudio/ComfyUI-Model-Backups:Q4_K_S

Run and chat with the model

lemonade run user.ComfyUI-Model-Backups-Q4_K_S

List all available models

lemonade list

ComfyUI Model Backups

Personal backup of the model collection used with ComfyUI. Files are organized into a labeled subfolder per model type, mirroring the standard ComfyUI models/ directory layout.

Folder layout

Each subfolder corresponds to a ComfyUI model type:

Subfolder	Model type
`text_encoders/`	Text encoder weights (T5, UMT5, Qwen-VL, …)
`clip/`	CLIP models
`clip_vision/`	CLIP vision models
`checkpoints/`	Full checkpoints
`diffusion_models/`	Diffusion model weights
`unet/`	UNet weights
`loras/`	LoRA adapters
`controlnet/`	ControlNet models
`vae/`	VAE models
`LLM/`	Language models
`…`	Additional types added folder by folder

Folders are uploaded incrementally, one type at a time. Not all types may be present yet.

Notes

These are model weight files (.safetensors, .gguf, etc.) kept for backup/restore convenience. Original licenses and terms belong to the respective model authors.
To restore a type, download its subfolder back into your ComfyUI models/<type>/ directory.

Downloads last month: 2

GGUF

Model size

8B params

Architecture

qwen2vl

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

8-bit

View +4 variants

Inference Providers NEW

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