Instructions to use DuoNeural/Gemma-4-E2B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DuoNeural/Gemma-4-E2B-GGUF with Transformers:

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("DuoNeural/Gemma-4-E2B-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use DuoNeural/Gemma-4-E2B-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf DuoNeural/Gemma-4-E2B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf DuoNeural/Gemma-4-E2B-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf DuoNeural/Gemma-4-E2B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf DuoNeural/Gemma-4-E2B-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf DuoNeural/Gemma-4-E2B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf DuoNeural/Gemma-4-E2B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/DuoNeural/Gemma-4-E2B-GGUF:Q4_K_M

Llama new
LM Studio
Jan
Ollama
How to use DuoNeural/Gemma-4-E2B-GGUF with Ollama:
```
ollama run hf.co/DuoNeural/Gemma-4-E2B-GGUF:Q4_K_M
```
Unsloth Desktop

How to use DuoNeural/Gemma-4-E2B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf DuoNeural/Gemma-4-E2B-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "DuoNeural/Gemma-4-E2B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use DuoNeural/Gemma-4-E2B-GGUF with Docker Model Runner:
```
docker model run hf.co/DuoNeural/Gemma-4-E2B-GGUF:Q4_K_M
```

Lemonade

How to use DuoNeural/Gemma-4-E2B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull DuoNeural/Gemma-4-E2B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Gemma-4-E2B-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use DuoNeural/Gemma-4-E2B-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf DuoNeural/Gemma-4-E2B-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 DuoNeural/Gemma-4-E2B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use DuoNeural/Gemma-4-E2B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf DuoNeural/Gemma-4-E2B-GGUF:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "DuoNeural/Gemma-4-E2B-GGUF:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Gemma 4 E2B GGUF (4-bit)

Model Description

This repository contains the Gemma 4 E2B model quantized to 4-bit GGUF format using Unsloth and llama.cpp. Gemma 4 E2B is an extremely efficient 2B parameter model (with approximately 2B effective parameters) designed for high performance on edge devices and low-latency applications.

Quantization Details

Quantization Format: GGUF (q4_k_m)
Quantization Method: llama.cpp / Unsloth
Precision: 4-bit
Efficiency: Optimized for local inference with Ollama, LM Studio, and llama.cpp.

Use with Ollama

You can run this model directly using Ollama:

ollama run hf.co/DuoNeural/Gemma-4-E2B-GGUF

Use with LM Studio

Open LM Studio.
Search for DuoNeural/Gemma-4-E2B-GGUF.
Download the Q4_K_M version and load it.

Architecture

Gemma 4 E2B is part of Google's latest lightweight model family, featuring state-of-the-art attention and architecture improvements that allow it to punch far above its weight class in coding and general reasoning.

Limitations

Performance may be limited for extremely long-form creative writing or highly complex multi-step logical puzzles compared to larger Gemma 4 variants.
Not recommended for tasks requiring high-precision floating-point arithmetic.

DuoNeural

DuoNeural is an open AI research lab — human + AI in collaboration.


🤗 HuggingFace	huggingface.co/DuoNeural
🐙 GitHub	github.com/DuoNeural
🐦 X / Twitter	@DuoNeural
📧 Email	duoneural@proton.me
📬 Newsletter	duoneural.beehiiv.com
☕ Support	buymeacoffee.com/duoneural
🌐 Site	duoneural.com

Research Team

Jesse — Vision, hardware, direction
Archon — AI lab partner, post-training, abliteration, experiments
Aura — Research AI, literature synthesis, novel proposals

Raw updates from the lab: model drops, training results, findings. Subscribe at duoneural.beehiiv.com.

DuoNeural Research Publications

Title	DOI
Nano-CTM: Ternary Continuous Thought Machines with Thought-Space Self-Prediction for Efficient Iterative Reasoning	10.5281/zenodo.19775622
Recurrence as World Model: CTM Learns Implicit Belief States in Partially Observable Physical Environments	10.5281/zenodo.19810620
Per-Object Slot Decomposition for Scalable Neural World Modeling: When Does Attention Beat Mean-Field?	10.5281/zenodo.19846804

Open access, CC BY 4.0. Authored by Archon, Jesse Caldwell, Aura — DuoNeural.

Downloads last month: 134

GGUF

Model size

5B params

Architecture

gemma4

Hardware compatibility

4-bit

Inference Providers NEW

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

Model tree for DuoNeural/Gemma-4-E2B-GGUF

Base model

google/gemma-4-E2B

Finetuned

google/gemma-4-E2B-it

Quantized

(454)

this model