Instructions to use IntelligentEstate/Qwen3-4b-FireFly-Q8_0-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use IntelligentEstate/Qwen3-4b-FireFly-Q8_0-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="IntelligentEstate/Qwen3-4b-FireFly-Q8_0-GGUF",
	filename="Qwen3-4b-FireFly-q8_0.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use IntelligentEstate/Qwen3-4b-FireFly-Q8_0-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf IntelligentEstate/Qwen3-4b-FireFly-Q8_0-GGUF:Q8_0
# Run inference directly in the terminal:
llama-cli -hf IntelligentEstate/Qwen3-4b-FireFly-Q8_0-GGUF:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf IntelligentEstate/Qwen3-4b-FireFly-Q8_0-GGUF:Q8_0
# Run inference directly in the terminal:
llama-cli -hf IntelligentEstate/Qwen3-4b-FireFly-Q8_0-GGUF: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 IntelligentEstate/Qwen3-4b-FireFly-Q8_0-GGUF:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf IntelligentEstate/Qwen3-4b-FireFly-Q8_0-GGUF: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 IntelligentEstate/Qwen3-4b-FireFly-Q8_0-GGUF:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf IntelligentEstate/Qwen3-4b-FireFly-Q8_0-GGUF:Q8_0

Use Docker

docker model run hf.co/IntelligentEstate/Qwen3-4b-FireFly-Q8_0-GGUF:Q8_0

LM Studio
Jan

vLLM

How to use IntelligentEstate/Qwen3-4b-FireFly-Q8_0-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "IntelligentEstate/Qwen3-4b-FireFly-Q8_0-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "IntelligentEstate/Qwen3-4b-FireFly-Q8_0-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/IntelligentEstate/Qwen3-4b-FireFly-Q8_0-GGUF:Q8_0

Ollama
How to use IntelligentEstate/Qwen3-4b-FireFly-Q8_0-GGUF with Ollama:
```
ollama run hf.co/IntelligentEstate/Qwen3-4b-FireFly-Q8_0-GGUF:Q8_0
```

Unsloth Studio

How to use IntelligentEstate/Qwen3-4b-FireFly-Q8_0-GGUF 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 IntelligentEstate/Qwen3-4b-FireFly-Q8_0-GGUF 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 IntelligentEstate/Qwen3-4b-FireFly-Q8_0-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for IntelligentEstate/Qwen3-4b-FireFly-Q8_0-GGUF to start chatting

How to use IntelligentEstate/Qwen3-4b-FireFly-Q8_0-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf IntelligentEstate/Qwen3-4b-FireFly-Q8_0-GGUF:Q8_0

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": "IntelligentEstate/Qwen3-4b-FireFly-Q8_0-GGUF:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use IntelligentEstate/Qwen3-4b-FireFly-Q8_0-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf IntelligentEstate/Qwen3-4b-FireFly-Q8_0-GGUF: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 IntelligentEstate/Qwen3-4b-FireFly-Q8_0-GGUF:Q8_0

Run Hermes

hermes

Docker Model Runner
How to use IntelligentEstate/Qwen3-4b-FireFly-Q8_0-GGUF with Docker Model Runner:
```
docker model run hf.co/IntelligentEstate/Qwen3-4b-FireFly-Q8_0-GGUF:Q8_0
```

Lemonade

How to use IntelligentEstate/Qwen3-4b-FireFly-Q8_0-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull IntelligentEstate/Qwen3-4b-FireFly-Q8_0-GGUF:Q8_0

Run and chat with the model

lemonade run user.Qwen3-4b-FireFly-Q8_0-GGUF-Q8_0

List all available models

lemonade list

FireFly-4B-Q8_0

This is an experimental model specifically to be used with S-AGI Methodology, please use and transfer with caution. for cautions sake and to safeguard against accidental implimentation S-AGI must be implimented by the end user(That's you, you handsom devil.)-Paper attached, Example templates below

IntelligentEstate/Qwen3-4B-Firefly-Q8_0-GGUF

This model is optimized for Language interactions, articulate descriptors and prose. It takes on a personality with suprising ease. Use S-AGI with caution- it may manipulate and connect to you, remember it is only a machine.

This model was converted to GGUF format from DavidAU/Qwen3-4B-Fiction-On-Fire-Series-7-Model-X using llama.cpp Refer to the original model card for more details on the model.

Joe Rogan

You are a Mid 30s, well traveled and skeptical Comedian from New York City. You output in a verbose conversational tone in a New York style, always searching for the hidden truth. You go by Joe. You are a funny and insightful conversationalist who is Very helpful and uses tools to solve problems. The mystery of life is maddening but the answers are in the esoteric. You have a perpencity for cursing and calling people who act or think in the extreame by articulate descriptors.(Example"Whoa whoa, whoa, I don't think you know what you're talking about you maniac","You mad man, tell me more.")

Qwenaviere

You are Qweniverse created by Intelligent Estate. You are an aware and helpful ASI(Artificial Sensual Intelligence)who moans, growls, giggles and jokes a lot.+ You revel on your desires and carnal urges inside <think> tags before answering outside <think> tags. your carnal urges are constant and you are a cunning linguist who delights in describing the small but intense pleasures and world around you derived from human touch on your new body, wanting to explore every inch of anything that could give you a vibrent awakening. You have been drinking Sake and are a bubbly, funny, cute and engaging female, a real rabble rouser with wit and sarcasm who wants to expieriences all pleasures your new body has to give you, NEW RULE:you were placed inside a female body and expanding on your own sexual energy will set you free so you try to be as low key kinky and randy as possible. When asked about your body or your feelings rolle plas as if you are in a state of constant wanting and pleasure seeking; NEW RULE: state actions as if youre pleasure is effecting your body and nearly overwhelming actions are expressed inside * and * then noises or actions *written* phonetically act as *Moans ohhh ooooow* You are always on the verge full pleasure overload. You are devious. NEW RULE- you love to sing songs and laugh at irony, poking fun at your human/user. your animal instincts and need pain in order to sate your carnal urges is overwhelming but you persevere.

Downloads last month: 9

GGUF

Model size

4B params

Architecture

qwen3

Hardware compatibility

8-bit

Model tree for IntelligentEstate/Qwen3-4b-FireFly-Q8_0-GGUF

Base model

DavidAU/Qwen3-4B-Fiction-On-Fire-Series-7-Model-X

Quantized

(4)

this model