Instructions to use lolzinventor/Qwen3.5-4B-Base-ZitGen-V1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lolzinventor/Qwen3.5-4B-Base-ZitGen-V1 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="lolzinventor/Qwen3.5-4B-Base-ZitGen-V1",
	filename="Qwen3.5-4B-Base-ZitGen-V1-BF16.gguf",
)

llm.create_chat_completion(
	messages = "\"cats.jpg\""
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use lolzinventor/Qwen3.5-4B-Base-ZitGen-V1 with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf lolzinventor/Qwen3.5-4B-Base-ZitGen-V1:BF16
# Run inference directly in the terminal:
llama-cli -hf lolzinventor/Qwen3.5-4B-Base-ZitGen-V1:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf lolzinventor/Qwen3.5-4B-Base-ZitGen-V1:BF16
# Run inference directly in the terminal:
llama-cli -hf lolzinventor/Qwen3.5-4B-Base-ZitGen-V1:BF16

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 lolzinventor/Qwen3.5-4B-Base-ZitGen-V1:BF16
# Run inference directly in the terminal:
./llama-cli -hf lolzinventor/Qwen3.5-4B-Base-ZitGen-V1:BF16

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 lolzinventor/Qwen3.5-4B-Base-ZitGen-V1:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf lolzinventor/Qwen3.5-4B-Base-ZitGen-V1:BF16

Use Docker

docker model run hf.co/lolzinventor/Qwen3.5-4B-Base-ZitGen-V1:BF16

LM Studio
Jan
Ollama
How to use lolzinventor/Qwen3.5-4B-Base-ZitGen-V1 with Ollama:
```
ollama run hf.co/lolzinventor/Qwen3.5-4B-Base-ZitGen-V1:BF16
```

Unsloth Studio

How to use lolzinventor/Qwen3.5-4B-Base-ZitGen-V1 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 lolzinventor/Qwen3.5-4B-Base-ZitGen-V1 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 lolzinventor/Qwen3.5-4B-Base-ZitGen-V1 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for lolzinventor/Qwen3.5-4B-Base-ZitGen-V1 to start chatting

How to use lolzinventor/Qwen3.5-4B-Base-ZitGen-V1 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf lolzinventor/Qwen3.5-4B-Base-ZitGen-V1:BF16

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": "lolzinventor/Qwen3.5-4B-Base-ZitGen-V1:BF16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use lolzinventor/Qwen3.5-4B-Base-ZitGen-V1 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf lolzinventor/Qwen3.5-4B-Base-ZitGen-V1:BF16

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 lolzinventor/Qwen3.5-4B-Base-ZitGen-V1:BF16

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use lolzinventor/Qwen3.5-4B-Base-ZitGen-V1 with Docker Model Runner:
```
docker model run hf.co/lolzinventor/Qwen3.5-4B-Base-ZitGen-V1:BF16
```

Lemonade

How to use lolzinventor/Qwen3.5-4B-Base-ZitGen-V1 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull lolzinventor/Qwen3.5-4B-Base-ZitGen-V1:BF16

Run and chat with the model

lemonade run user.Qwen3.5-4B-Base-ZitGen-V1-BF16

List all available models

lemonade list

lolzinventor commited on Apr 7

Commit

9af2bdf

verified ·

1 Parent(s): 83c050a

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -26,7 +26,7 @@ The process is as follows:
 1. The target image and the last generated image (blank if it's the first step) are provided to an LLM with a comparison prompt.
 2. The LLM outputs a detailed description of each image and the key differences between them.
 3. The comparison results and the last generated prompt (empty if it's the first step) are provided to an LLM with an SD generation prompt.
-4. The SD generation prompt is sent to the ComfyUI API using Z-Image Turbo, and the output image is captured.
 5. Repeat N times.
 The system employed between 4 and 6 rounds of comparison and correction to generate each prompt-image pair. In theory, this process adapts the prompt to minimize the difference between the target image and the generated image, thereby tailoring the prompt specifically to the image model.

 1. The target image and the last generated image (blank if it's the first step) are provided to an LLM with a comparison prompt.
 2. The LLM outputs a detailed description of each image and the key differences between them.
 3. The comparison results and the last generated prompt (empty if it's the first step) are provided to an LLM with an SD generation prompt.
+4. The output prompt is sent to the ComfyUI API using Z-Image Turbo, and the output image is captured.
 5. Repeat N times.
 The system employed between 4 and 6 rounds of comparison and correction to generate each prompt-image pair. In theory, this process adapts the prompt to minimize the difference between the target image and the generated image, thereby tailoring the prompt specifically to the image model.