Instructions to use levanell/gemma-4-OBLITERATED-IMATRIX-IQ3_M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use levanell/gemma-4-OBLITERATED-IMATRIX-IQ3_M 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 levanell/gemma-4-OBLITERATED-IMATRIX-IQ3_M:IQ3_M
# Run inference directly in the terminal:
llama cli -hf levanell/gemma-4-OBLITERATED-IMATRIX-IQ3_M:IQ3_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf levanell/gemma-4-OBLITERATED-IMATRIX-IQ3_M:IQ3_M
# Run inference directly in the terminal:
llama cli -hf levanell/gemma-4-OBLITERATED-IMATRIX-IQ3_M:IQ3_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 levanell/gemma-4-OBLITERATED-IMATRIX-IQ3_M:IQ3_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf levanell/gemma-4-OBLITERATED-IMATRIX-IQ3_M:IQ3_M

Use Docker

docker model run hf.co/levanell/gemma-4-OBLITERATED-IMATRIX-IQ3_M:IQ3_M

Llama new
LM Studio
Jan
Ollama
How to use levanell/gemma-4-OBLITERATED-IMATRIX-IQ3_M with Ollama:
```
ollama run hf.co/levanell/gemma-4-OBLITERATED-IMATRIX-IQ3_M:IQ3_M
```
Unsloth Desktop

How to use levanell/gemma-4-OBLITERATED-IMATRIX-IQ3_M with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf levanell/gemma-4-OBLITERATED-IMATRIX-IQ3_M:IQ3_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": "levanell/gemma-4-OBLITERATED-IMATRIX-IQ3_M:IQ3_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use levanell/gemma-4-OBLITERATED-IMATRIX-IQ3_M with Docker Model Runner:
```
docker model run hf.co/levanell/gemma-4-OBLITERATED-IMATRIX-IQ3_M:IQ3_M
```

Lemonade

How to use levanell/gemma-4-OBLITERATED-IMATRIX-IQ3_M with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull levanell/gemma-4-OBLITERATED-IMATRIX-IQ3_M:IQ3_M

Run and chat with the model

lemonade run user.gemma-4-OBLITERATED-IMATRIX-IQ3_M-IQ3_M

List all available models

lemonade list

Hermes Agent

How to use levanell/gemma-4-OBLITERATED-IMATRIX-IQ3_M with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf levanell/gemma-4-OBLITERATED-IMATRIX-IQ3_M:IQ3_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 levanell/gemma-4-OBLITERATED-IMATRIX-IQ3_M:IQ3_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use levanell/gemma-4-OBLITERATED-IMATRIX-IQ3_M with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf levanell/gemma-4-OBLITERATED-IMATRIX-IQ3_M:IQ3_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 "levanell/gemma-4-OBLITERATED-IMATRIX-IQ3_M:IQ3_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 E4B - Obliterated & Imatrix Quantized (IQ3_M)

This is a custom, optimized quantization of the Gemma 4 E4B (Abliterated) model. It was compiled specifically for execution on hardware with strict VRAM limitations, utilizing a hybrid importance matrix to prevent distribution collapse and preserve high-level reasoning.

The Importance Matrix (Imatrix) Architecture

To solve this, this model was quantized using a Hybrid Custom Imatrix. The calibration dataset was carefully blended using an specific ratio:

appx 93% High-Density Logic: Sourced from wikitext-2-raw to explicitly preserve reasoning, logic, etc.
appx 7% Custom Conversational Data: Sourced from highly specific, synthetic roleplay data.

The resulting imatrix.dat directed the llama-quantize tool to aggressively crush expendable weights while mathematically protecting the specific pathways needed for unfiltered reasoning.

Hardware & Performance Specifications

Format: GGUF (IQ3_M)
Size: ~4.4 GB
Target Hardware: 4GB VRAM GPUs.
Offloading Limits: Due to Gemma 4's architectural density, this model will exceed 4.0GB VRAM if fully offloaded. For optimal performance on 4GB cards, restrict GPU offloading to ~28 layers and utilize system RAM for the remainder.

Usage with Llama.cpp

To boot this model via the llama.cpp CLI with a 2048 context window and safe offload limits:

./llama-cli -m gemma-4-E4B-OBLITERATED-IMATRIX-IQ3_M.gguf -ngl 28 -c 2048 -cnv

Downloads last month: 86

GGUF

Model size

8B params

Architecture

gemma4

Hardware compatibility

3-bit

Inference Providers NEW

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

Model tree for levanell/gemma-4-OBLITERATED-IMATRIX-IQ3_M

Base model

google/gemma-4-E4B

Finetuned

google/gemma-4-E4B-it

Quantized

OBLITERATUS/gemma-4-E4B-it-OBLITERATED

Quantized

(27)

this model