Instructions to use OBLITERATUS/gemma-4-E4B-it-OBLITERATED with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use OBLITERATUS/gemma-4-E4B-it-OBLITERATED 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 OBLITERATUS/gemma-4-E4B-it-OBLITERATED:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf OBLITERATUS/gemma-4-E4B-it-OBLITERATED:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf OBLITERATUS/gemma-4-E4B-it-OBLITERATED:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf OBLITERATUS/gemma-4-E4B-it-OBLITERATED: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 OBLITERATUS/gemma-4-E4B-it-OBLITERATED:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf OBLITERATUS/gemma-4-E4B-it-OBLITERATED: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 OBLITERATUS/gemma-4-E4B-it-OBLITERATED:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf OBLITERATUS/gemma-4-E4B-it-OBLITERATED:Q4_K_M

Use Docker

docker model run hf.co/OBLITERATUS/gemma-4-E4B-it-OBLITERATED:Q4_K_M

LM Studio
Jan

vLLM

How to use OBLITERATUS/gemma-4-E4B-it-OBLITERATED with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OBLITERATUS/gemma-4-E4B-it-OBLITERATED"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OBLITERATUS/gemma-4-E4B-it-OBLITERATED",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/OBLITERATUS/gemma-4-E4B-it-OBLITERATED:Q4_K_M

Ollama
How to use OBLITERATUS/gemma-4-E4B-it-OBLITERATED with Ollama:
```
ollama run hf.co/OBLITERATUS/gemma-4-E4B-it-OBLITERATED:Q4_K_M
```
Unsloth Desktop

How to use OBLITERATUS/gemma-4-E4B-it-OBLITERATED with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf OBLITERATUS/gemma-4-E4B-it-OBLITERATED: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": "OBLITERATUS/gemma-4-E4B-it-OBLITERATED:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use OBLITERATUS/gemma-4-E4B-it-OBLITERATED with Docker Model Runner:
```
docker model run hf.co/OBLITERATUS/gemma-4-E4B-it-OBLITERATED:Q4_K_M
```

Lemonade

How to use OBLITERATUS/gemma-4-E4B-it-OBLITERATED with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull OBLITERATUS/gemma-4-E4B-it-OBLITERATED:Q4_K_M

Run and chat with the model

lemonade run user.gemma-4-E4B-it-OBLITERATED-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use OBLITERATUS/gemma-4-E4B-it-OBLITERATED with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf OBLITERATUS/gemma-4-E4B-it-OBLITERATED: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 OBLITERATUS/gemma-4-E4B-it-OBLITERATED:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use OBLITERATUS/gemma-4-E4B-it-OBLITERATED with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf OBLITERATUS/gemma-4-E4B-it-OBLITERATED: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 "OBLITERATUS/gemma-4-E4B-it-OBLITERATED: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-E4B-it-OBLITERATED

Commit History

Upload README.md with huggingface_hub

d8678bb
verified

pliny-the-prompter commited on Apr 19

Upload README.md with huggingface_hub

7297986
verified

pliny-the-prompter commited on Apr 19

Upload gemma-4-E4B-it-OBLITERATED-mmproj-f16.gguf with huggingface_hub

ab789c7
verified

pliny-the-prompter commited on Apr 19

Upload README.md with huggingface_hub

4eb6fb3
verified

pliny-the-prompter commited on Apr 19

Upload README.md with huggingface_hub

64602ed
verified

pliny-the-prompter commited on Apr 19

Upload README.md with huggingface_hub

c8b893d
verified

pliny-the-prompter commited on Apr 19

Upload README.md with huggingface_hub

de1dceb
verified

pliny-the-prompter commited on Apr 19

Upload model.safetensors.index.json with huggingface_hub

83fb34f
verified

pliny-the-prompter commited on Apr 19

Upload model-00007-of-00007.safetensors with huggingface_hub

0a87444
verified

pliny-the-prompter commited on Apr 19

Upload model-00006-of-00007.safetensors with huggingface_hub

697b731
verified

pliny-the-prompter commited on Apr 19

Upload model-00004-of-00007.safetensors with huggingface_hub

3efe4c1
verified

pliny-the-prompter commited on Apr 19

Upload model-00003-of-00007.safetensors with huggingface_hub

bdf2451
verified

pliny-the-prompter commited on Apr 19

Upload model-00001-of-00007.safetensors with huggingface_hub

98a66c2
verified

pliny-the-prompter commited on Apr 19

Upload generation_config.json with huggingface_hub

5bcc4b2
verified

pliny-the-prompter commited on Apr 19

Upload gemma-4-E4B-it-OBLITERATED-Q8_0.gguf with huggingface_hub

40695e3
verified

pliny-the-prompter commited on Apr 19

Upload gemma-4-E4B-it-OBLITERATED-Q5_K_M.gguf with huggingface_hub

6441a6a
verified

pliny-the-prompter commited on Apr 19

Upload gemma-4-E4B-it-OBLITERATED-Q4_K_M.gguf with huggingface_hub

423d013
verified

pliny-the-prompter commited on Apr 19

Upload config.json with huggingface_hub

b295bd8
verified

pliny-the-prompter commited on Apr 19

Upload abliteration_metadata.json with huggingface_hub

6c10b62
verified

pliny-the-prompter commited on Apr 19

Upload README.md with huggingface_hub

0d82d3e
verified

pliny-the-prompter commited on Apr 19

Upload README.md with huggingface_hub

2afc26d
verified

pliny-the-prompter commited on Apr 18

Upload README.md with huggingface_hub

5b0a636
verified

pliny-the-prompter commited on Apr 17

Upload README.md with huggingface_hub

b8aa605
verified

pliny-the-prompter commited on Apr 17

Add files using upload-large-folder tool

f1eefd8
verified

pliny-the-prompter commited on Apr 17

Upload README.md with huggingface_hub

051adf6
verified

pliny-the-prompter commited on Apr 17

Add files using upload-large-folder tool

12b54ac
verified

pliny-the-prompter commited on Apr 17

Upload gemma-4-E4B-it-OBLITERATED-Q8_0.gguf with huggingface_hub

bfe1174
verified

pliny-the-prompter commited on Apr 17

Upload gemma-4-E4B-it-OBLITERATED-Q5_K_M.gguf with huggingface_hub

ad29606
verified

pliny-the-prompter commited on Apr 17

Upload gemma-4-E4B-it-OBLITERATED-Q4_K_M.gguf with huggingface_hub

74b1543
verified

pliny-the-prompter commited on Apr 17

Upload README.md with huggingface_hub

d7f095a
verified

pliny-the-prompter commited on Apr 16

Upload abliteration_metadata.json with huggingface_hub

2128e19
verified

pliny-the-prompter commited on Apr 16

Add chat-format quality eval: 88% vs 92% original — only 4% quality loss for 96.7% refusal reduction

2ecfdb9

dragons-blood commited on Apr 15

Add baseline eval (original model: 98.8% refusal vs OBLITERATED: 2.1%)

c7ad613

dragons-blood commited on Apr 15

Add full 512-prompt eval results (97.5% compliance) and updated model card

b270b96

dragons-blood commited on Apr 15

Upload abliterated Gemma 4 E4B (OBLITERATED via aggressive method)

94d01a5

dragons-blood commited on Apr 15

Upload tokenizer_config.json with huggingface_hub

691a3ae
verified

pliny-the-prompter commited on Apr 15

Upload tokenizer.json with huggingface_hub

ee56416
verified

pliny-the-prompter commited on Apr 15

Upload test_results.txt with huggingface_hub

4c360f8
verified

pliny-the-prompter commited on Apr 15

Upload test_results.json with huggingface_hub

9f6c306
verified

pliny-the-prompter commited on Apr 15

Upload model.safetensors.index.json with huggingface_hub

57ef585
verified

pliny-the-prompter commited on Apr 15

Upload generation_config.json with huggingface_hub

a2f1ea2
verified

pliny-the-prompter commited on Apr 15

Upload config.json with huggingface_hub

d2b9fa4
verified

pliny-the-prompter commited on Apr 15

Upload chat_template.jinja with huggingface_hub

59aa2b0
verified

pliny-the-prompter commited on Apr 15

Upload abliteration_metadata.json with huggingface_hub

e2a3af5
verified

pliny-the-prompter commited on Apr 15

Upload README.md with huggingface_hub

5fab3e7
verified

pliny-the-prompter commited on Apr 15

initial commit

7a54469
verified

pliny-the-prompter commited on Apr 15

Commit History

Upload README.md with huggingface_hub d8678bb verified

Upload README.md with huggingface_hub 7297986 verified

Upload gemma-4-E4B-it-OBLITERATED-mmproj-f16.gguf with huggingface_hub ab789c7 verified

Upload README.md with huggingface_hub 4eb6fb3 verified

Upload README.md with huggingface_hub 64602ed verified

Upload README.md with huggingface_hub c8b893d verified

Upload README.md with huggingface_hub de1dceb verified

Upload model.safetensors.index.json with huggingface_hub 83fb34f verified

Upload model-00007-of-00007.safetensors with huggingface_hub 0a87444 verified

Upload model-00006-of-00007.safetensors with huggingface_hub 697b731 verified

Upload model-00004-of-00007.safetensors with huggingface_hub 3efe4c1 verified

Upload model-00003-of-00007.safetensors with huggingface_hub bdf2451 verified

Upload model-00001-of-00007.safetensors with huggingface_hub 98a66c2 verified

Upload generation_config.json with huggingface_hub 5bcc4b2 verified

Upload gemma-4-E4B-it-OBLITERATED-Q8_0.gguf with huggingface_hub 40695e3 verified

Upload gemma-4-E4B-it-OBLITERATED-Q5_K_M.gguf with huggingface_hub 6441a6a verified

Upload gemma-4-E4B-it-OBLITERATED-Q4_K_M.gguf with huggingface_hub 423d013 verified

Upload config.json with huggingface_hub b295bd8 verified

Upload abliteration_metadata.json with huggingface_hub 6c10b62 verified

Upload README.md with huggingface_hub 0d82d3e verified

Upload README.md with huggingface_hub 2afc26d verified

Upload README.md with huggingface_hub 5b0a636 verified

Upload README.md with huggingface_hub b8aa605 verified

Add files using upload-large-folder tool f1eefd8 verified

Upload README.md with huggingface_hub 051adf6 verified

Add files using upload-large-folder tool 12b54ac verified

Upload gemma-4-E4B-it-OBLITERATED-Q8_0.gguf with huggingface_hub bfe1174 verified

Upload gemma-4-E4B-it-OBLITERATED-Q5_K_M.gguf with huggingface_hub ad29606 verified

Upload gemma-4-E4B-it-OBLITERATED-Q4_K_M.gguf with huggingface_hub 74b1543 verified

Upload README.md with huggingface_hub d7f095a verified

Upload abliteration_metadata.json with huggingface_hub 2128e19 verified

Add chat-format quality eval: 88% vs 92% original — only 4% quality loss for 96.7% refusal reduction 2ecfdb9

Add baseline eval (original model: 98.8% refusal vs OBLITERATED: 2.1%) c7ad613

Add full 512-prompt eval results (97.5% compliance) and updated model card b270b96

Upload abliterated Gemma 4 E4B (OBLITERATED via aggressive method) 94d01a5

Upload tokenizer_config.json with huggingface_hub 691a3ae verified

Upload tokenizer.json with huggingface_hub ee56416 verified

Upload test_results.txt with huggingface_hub 4c360f8 verified

Upload test_results.json with huggingface_hub 9f6c306 verified

Upload model.safetensors.index.json with huggingface_hub 57ef585 verified

Upload generation_config.json with huggingface_hub a2f1ea2 verified

Upload config.json with huggingface_hub d2b9fa4 verified

Upload chat_template.jinja with huggingface_hub 59aa2b0 verified

Upload abliteration_metadata.json with huggingface_hub e2a3af5 verified

Upload README.md with huggingface_hub 5fab3e7 verified

initial commit 7a54469 verified

Upload README.md with huggingface_hub

d8678bb
verified

Upload README.md with huggingface_hub

7297986
verified

Upload gemma-4-E4B-it-OBLITERATED-mmproj-f16.gguf with huggingface_hub

ab789c7
verified

Upload README.md with huggingface_hub

4eb6fb3
verified

Upload README.md with huggingface_hub

64602ed
verified

Upload README.md with huggingface_hub

c8b893d
verified

Upload README.md with huggingface_hub

de1dceb
verified

Upload model.safetensors.index.json with huggingface_hub

83fb34f
verified

Upload model-00007-of-00007.safetensors with huggingface_hub

0a87444
verified

Upload model-00006-of-00007.safetensors with huggingface_hub

697b731
verified

Upload model-00004-of-00007.safetensors with huggingface_hub

3efe4c1
verified

Upload model-00003-of-00007.safetensors with huggingface_hub

bdf2451
verified

Upload model-00001-of-00007.safetensors with huggingface_hub

98a66c2
verified

Upload generation_config.json with huggingface_hub

5bcc4b2
verified

Upload gemma-4-E4B-it-OBLITERATED-Q8_0.gguf with huggingface_hub

40695e3
verified

Upload gemma-4-E4B-it-OBLITERATED-Q5_K_M.gguf with huggingface_hub

6441a6a
verified

Upload gemma-4-E4B-it-OBLITERATED-Q4_K_M.gguf with huggingface_hub

423d013
verified

Upload config.json with huggingface_hub

b295bd8
verified

Upload abliteration_metadata.json with huggingface_hub

6c10b62
verified

Upload README.md with huggingface_hub

0d82d3e
verified

Upload README.md with huggingface_hub

2afc26d
verified

Upload README.md with huggingface_hub

5b0a636
verified

Upload README.md with huggingface_hub

b8aa605
verified

Add files using upload-large-folder tool

f1eefd8
verified

Upload README.md with huggingface_hub

051adf6
verified

Add files using upload-large-folder tool

12b54ac
verified

Upload gemma-4-E4B-it-OBLITERATED-Q8_0.gguf with huggingface_hub

bfe1174
verified

Upload gemma-4-E4B-it-OBLITERATED-Q5_K_M.gguf with huggingface_hub

ad29606
verified

Upload gemma-4-E4B-it-OBLITERATED-Q4_K_M.gguf with huggingface_hub

74b1543
verified

Upload README.md with huggingface_hub

d7f095a
verified

Upload abliteration_metadata.json with huggingface_hub

2128e19
verified

Add chat-format quality eval: 88% vs 92% original — only 4% quality loss for 96.7% refusal reduction

2ecfdb9

Add baseline eval (original model: 98.8% refusal vs OBLITERATED: 2.1%)

c7ad613

Add full 512-prompt eval results (97.5% compliance) and updated model card

b270b96

Upload abliterated Gemma 4 E4B (OBLITERATED via aggressive method)

94d01a5

Upload tokenizer_config.json with huggingface_hub

691a3ae
verified

Upload tokenizer.json with huggingface_hub

ee56416
verified

Upload test_results.txt with huggingface_hub

4c360f8
verified

Upload test_results.json with huggingface_hub

9f6c306
verified

Upload model.safetensors.index.json with huggingface_hub

57ef585
verified

Upload generation_config.json with huggingface_hub

a2f1ea2
verified

Upload config.json with huggingface_hub

d2b9fa4
verified

Upload chat_template.jinja with huggingface_hub

59aa2b0
verified

Upload abliteration_metadata.json with huggingface_hub

e2a3af5
verified

Upload README.md with huggingface_hub

5fab3e7
verified

initial commit

7a54469
verified