Instructions to use DavidAU/Qwen3-4B-Hivemind-Instruct-NEO-MAX-Imatrix-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DavidAU/Qwen3-4B-Hivemind-Instruct-NEO-MAX-Imatrix-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="DavidAU/Qwen3-4B-Hivemind-Instruct-NEO-MAX-Imatrix-GGUF",
	filename="Qwen3-4B-Hivemind-Instruct-NeoMAX-D_AU-IQ2_M-imat.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use DavidAU/Qwen3-4B-Hivemind-Instruct-NEO-MAX-Imatrix-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf DavidAU/Qwen3-4B-Hivemind-Instruct-NEO-MAX-Imatrix-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf DavidAU/Qwen3-4B-Hivemind-Instruct-NEO-MAX-Imatrix-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf DavidAU/Qwen3-4B-Hivemind-Instruct-NEO-MAX-Imatrix-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf DavidAU/Qwen3-4B-Hivemind-Instruct-NEO-MAX-Imatrix-GGUF:Q4_K_M

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 DavidAU/Qwen3-4B-Hivemind-Instruct-NEO-MAX-Imatrix-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf DavidAU/Qwen3-4B-Hivemind-Instruct-NEO-MAX-Imatrix-GGUF:Q4_K_M

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 DavidAU/Qwen3-4B-Hivemind-Instruct-NEO-MAX-Imatrix-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf DavidAU/Qwen3-4B-Hivemind-Instruct-NEO-MAX-Imatrix-GGUF:Q4_K_M

Use Docker

docker model run hf.co/DavidAU/Qwen3-4B-Hivemind-Instruct-NEO-MAX-Imatrix-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use DavidAU/Qwen3-4B-Hivemind-Instruct-NEO-MAX-Imatrix-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DavidAU/Qwen3-4B-Hivemind-Instruct-NEO-MAX-Imatrix-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": "DavidAU/Qwen3-4B-Hivemind-Instruct-NEO-MAX-Imatrix-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/DavidAU/Qwen3-4B-Hivemind-Instruct-NEO-MAX-Imatrix-GGUF:Q4_K_M

Ollama
How to use DavidAU/Qwen3-4B-Hivemind-Instruct-NEO-MAX-Imatrix-GGUF with Ollama:
```
ollama run hf.co/DavidAU/Qwen3-4B-Hivemind-Instruct-NEO-MAX-Imatrix-GGUF:Q4_K_M
```

Unsloth Studio new

How to use DavidAU/Qwen3-4B-Hivemind-Instruct-NEO-MAX-Imatrix-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 DavidAU/Qwen3-4B-Hivemind-Instruct-NEO-MAX-Imatrix-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 DavidAU/Qwen3-4B-Hivemind-Instruct-NEO-MAX-Imatrix-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for DavidAU/Qwen3-4B-Hivemind-Instruct-NEO-MAX-Imatrix-GGUF to start chatting

Pi new

How to use DavidAU/Qwen3-4B-Hivemind-Instruct-NEO-MAX-Imatrix-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf DavidAU/Qwen3-4B-Hivemind-Instruct-NEO-MAX-Imatrix-GGUF:Q4_K_M

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": "DavidAU/Qwen3-4B-Hivemind-Instruct-NEO-MAX-Imatrix-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use DavidAU/Qwen3-4B-Hivemind-Instruct-NEO-MAX-Imatrix-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 DavidAU/Qwen3-4B-Hivemind-Instruct-NEO-MAX-Imatrix-GGUF:Q4_K_M

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 DavidAU/Qwen3-4B-Hivemind-Instruct-NEO-MAX-Imatrix-GGUF:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use DavidAU/Qwen3-4B-Hivemind-Instruct-NEO-MAX-Imatrix-GGUF with Docker Model Runner:
```
docker model run hf.co/DavidAU/Qwen3-4B-Hivemind-Instruct-NEO-MAX-Imatrix-GGUF:Q4_K_M
```

Lemonade

How to use DavidAU/Qwen3-4B-Hivemind-Instruct-NEO-MAX-Imatrix-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull DavidAU/Qwen3-4B-Hivemind-Instruct-NEO-MAX-Imatrix-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3-4B-Hivemind-Instruct-NEO-MAX-Imatrix-GGUF-Q4_K_M

List all available models

lemonade list

Qwen3-4B-Hivemind-Instruct-NEO-MAX-Imatrix-GGUF

The Storm is coming...

256k context, off the scale power.

NEO Imatrix with MAX quants (16 bit OT all quants).

This is the one that will make closed source sweat.

This is the one that will make them all sweat.

This is a general purpose model.

BENCHMARKS:


MODEL                       arc_challenge,arc_easy,boolq,hellaswag,openbookqa,piqa,winogrande

Our 4B Instruct Model       0.613,0.842,0.855,0.748,0.428,0.781,0.709
Qwen3-30B-A3B-Thinking-2507 0.421,0.448,0.682,0.635,0.402,0.771,0.669

WANT POWER (4B/6B/8B) without "the nanny" ?

https://huggingface.co/DavidAU/Qwen3-4B-Hivemind-Instruct-Heretic-Abliterated-Uncensored-NEO-Imatrix-GGUF

https://huggingface.co/DavidAU/Qwen3-6B-Hivemind-Instruct-Heretic-Abliterated-Uncensored-NEO-Imatrix-GGUF

https://huggingface.co/DavidAU/Qwen3-8B-Hivemind-Instruct-Heretic-Abliterated-Uncensored-NEO-Imatrix-GGUF

Special Thanks:

This was a Colab project between Nightmedia and DavidAU.

Nightmedia:

https://huggingface.co/nightmedia

Thanks to the following model makers/tuners (models used in this project):

https://huggingface.co/Gen-Verse/Qwen3-4B-RA-SFT

https://huggingface.co/TeichAI/Qwen3-4B-Instruct-2507-Polaris-Alpha-Distill

https://huggingface.co/TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill

And of course team Qwen:

https://huggingface.co/Qwen

Settings: CHAT / ROLEPLAY and/or SMOOTHER operation of this model:

In "KoboldCpp" or "oobabooga/text-generation-webui" or "Silly Tavern" ;

Set the "Smoothing_factor" to 1.5

: in KoboldCpp -> Settings->Samplers->Advanced-> "Smooth_F"

: in text-generation-webui -> parameters -> lower right.

: In Silly Tavern this is called: "Smoothing"

NOTE: For "text-generation-webui"

-> if using GGUFs you need to use "llama_HF" (which involves downloading some config files from the SOURCE version of this model)

Source versions (and config files) of my models are here:

https://huggingface.co/collections/DavidAU/d-au-source-files-for-gguf-exl2-awq-gptq-hqq-etc-etc-66b55cb8ba25f914cbf210be

OTHER OPTIONS:

Increase rep pen to 1.1 to 1.15 (you don't need to do this if you use "smoothing_factor")
If the interface/program you are using to run AI MODELS supports "Quadratic Sampling" ("smoothing") just make the adjustment as noted.

Highest Quality Settings / Optimal Operation Guide / Parameters and Samplers

This a "Class 1" model:

For all settings used for this model (including specifics for its "class"), including example generation(s) and for advanced settings guide (which many times addresses any model issue(s)), including methods to improve model performance for all use case(s) as well as chat, roleplay and other use case(s) please see:

[ https://huggingface.co/DavidAU/Maximizing-Model-Performance-All-Quants-Types-And-Full-Precision-by-Samplers_Parameters ]

You can see all parameters used for generation, in addition to advanced parameters and samplers to get the most out of this model here:

[ https://huggingface.co/DavidAU/Maximizing-Model-Performance-All-Quants-Types-And-Full-Precision-by-Samplers_Parameters ]