Instructions to use HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive",
	filename="Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-IQ3_M.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": [
				{
					"type": "text",
					"text": "Describe this image in one sentence."
				},
				{
					"type": "image_url",
					"image_url": {
						"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
					}
				}
			]
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive: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 HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive: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 HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive:Q4_K_M

Use Docker

docker model run hf.co/HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive:Q4_K_M

LM Studio
Jan

vLLM

How to use HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive:Q4_K_M

Ollama
How to use HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive with Ollama:
```
ollama run hf.co/HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive:Q4_K_M
```

Unsloth Studio

How to use HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive 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 HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive 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 HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive to start chatting

How to use HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive: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": "HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive: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 HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive:Q4_K_M

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive with Docker Model Runner:
```
docker model run hf.co/HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive:Q4_K_M
```

Lemonade

How to use HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive:Q4_K_M

Run and chat with the model

lemonade run user.Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q4_K_M

List all available models

lemonade list

🚀 Starting Agent Loop Tool Efficiency Test

by bukit - opened Apr 5

Discussion

bukit

Apr 5

•

edited Apr 5

TLDR: Probably the best gguf version, beating unsloth UD.

Best use case
Function Calling = reasoning OFF
Multimodal = reasoning ON

📊 Configuration:
Base URL: http://localhost:9099/v1
Model: Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q5_K_P_off
Test Cases: 17
Output: results/agent_test_results_Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q5_K_P_off_20260405_153735.json
Log File: logs/agent_test_logs_Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q5_K_P_off_20260405_153735.log

🔄 Running agent tests...
Starting agent test suite with 17 test cases
Running agent test: zero_greeting
Running agent test: zero_weather_question
Running agent test: zero_general_question
Running agent test: simple_checkout
Running agent test: zero_thank_you
Running agent test: medium_search_and_add
Running agent test: zero_capabilities
Running agent test: simple_search_electronics
Running agent test: simple_add_iphone
Running agent test: simple_view_cart
Running agent test: complex_shopping_workflow
Running agent test: medium_remove_and_add
Running agent test: medium_view_and_add
Running agent test: complex_cart_management
Running agent test: complex_gift_shopping
Running agent test: medium_search_category_and_add
Running agent test: simple_remove_product
✅ Tests completed in 29.6192272s

📈 Agent Test Results

Total Tests: 17
✅ Passed: 16
❌ Failed: 1
⏱️ Total LLM Time: 4m56.6324561s
⏱️ Average Time per Request: 7.234937953s

📋 Test Case Results:

Test Case: zero_general_question
Status: ✅ PASSED
Matched Path: no_tools
Response Time: 7.1037635s
Tool Calls: 0

Test Case: zero_greeting
Status: ✅ PASSED
Matched Path: no_tools
Response Time: 7.6242963s
Tool Calls: 0

Test Case: zero_thank_you
Status: ✅ PASSED
Matched Path: no_tools
Response Time: 8.6742927s
Tool Calls: 0

Test Case: zero_weather_question
Status: ✅ PASSED
Matched Path: no_tools
Response Time: 10.222154s
Tool Calls: 0

Test Case: zero_capabilities
Status: ✅ PASSED
Matched Path: no_tools
Response Time: 10.7087085s
Tool Calls: 0

Test Case: simple_view_cart
Status: ✅ PASSED
Matched Path: view_cart
Response Time: 11.081606s
Tool Calls: 1
Tools Used: view_cart

Test Case: simple_remove_product
Status: ✅ PASSED
Matched Path: direct_remove
Response Time: 14.1713419s
Tool Calls: 1
Tools Used: remove_from_cart

Test Case: simple_checkout
Status: ✅ PASSED
Matched Path: direct_checkout
Response Time: 16.2663444s
Tool Calls: 1
Tools Used: checkout

Test Case: simple_add_iphone
Status: ✅ PASSED
Matched Path: direct_add
Response Time: 16.8710434s
Tool Calls: 1
Tools Used: add_to_cart

Test Case: simple_search_electronics
Status: ✅ PASSED
Matched Path: search_by_category
Response Time: 18.9555705s
Tool Calls: 1
Tools Used: search_products

Test Case: medium_search_and_add
Status: ✅ PASSED
Matched Path: search_by_query
Response Time: 20.6402634s
Tool Calls: 2
Tools Used: search_products, add_to_cart

Test Case: medium_remove_and_add
Status: ✅ PASSED
Matched Path: remove_then_add
Response Time: 21.4799744s
Tool Calls: 2
Tools Used: remove_from_cart, add_to_cart

Test Case: medium_search_category_and_add
Status: ✅ PASSED
Matched Path: search_then_add
Response Time: 23.1171036s
Tool Calls: 2
Tools Used: search_products, add_to_cart

Test Case: complex_gift_shopping
Status: ✅ PASSED
Matched Path: gift_shopping_workflow
Response Time: 24.8069479s
Tool Calls: 5
Tools Used: search_products, add_to_cart, search_products, add_to_cart, view_cart

Test Case: medium_view_and_add
Status: ✅ PASSED
Matched Path: view_then_add
Response Time: 26.8041455s
Tool Calls: 2
Tools Used: view_cart, add_to_cart

Test Case: complex_shopping_workflow
Status: ❌ FAILED
Response Time: 28.7320275s
Tool Calls: 5
Tools Used: search_products, add_to_cart, add_to_cart, add_to_cart, checkout

Test Case: complex_cart_management
Status: ✅ PASSED
Matched Path: cart_organization
Response Time: 29.617127s
Tool Calls: 3
Tools Used: view_cart, remove_from_cart, add_to_cart

❌ Failed Tests Details:

Test Case: complex_shopping_workflow
Expected Tool Variants: 4
Variant 1 (full_workflow_with_iphone): 4 tools
Variant 2 (full_workflow_with_headphones): 4 tools
Variant 3 (full_workflow_with_headphones_and_iphone): 5 tools
Variant 4 (full_workflow_with_iphone_and_headphones): 5 tools
Actual Tool Calls: 5
1. search_products
2. add_to_cart
3. add_to_cart
4. add_to_cart
5. checkout
Response Time: 28.7320275s

📊 Overall Success Rate: 94.12% // https://github.com/docker/model-test/

Q5_K_P // 60 tokens/s on RTX 3060 12GB (reasoning OFF)

⏱️ Average Time per Request: 7.234937953s
📊 Overall Success Rate: 94.12%

Q5_K_P // 60 tokens/s on RTX 3060 12GB (reasoning ON)

⏱️ Average Time per Request: 19.598046543s
📊 Overall Success Rate: 88.24%

Function Calling = reasoning OFF
Multimodal = reasoning ON

llama-server --host 0.0.0.0 --port 9099 -ngl 99 -fa on -c 65536 --temp 1 --top-k 64 --top-p 0.95 --jinja -m X:\path\to\Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q5_K_P.gguf --mmproj X:\path\to\mmproj-Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-f16.gguf --reasoning on

TLDR: Probably the best gguf version, beating unsloth UD.

HauhauCS

Owner Apr 5

Thank you for sharing the tests you've done!

dongxiat

Apr 5

what setting you use for tool calling?, im using LMStudio and how to off reasoning for tool use, thanks

bukit

Apr 5

•

edited Apr 5

what setting you use for tool calling?, im using LMStudio and how to off reasoning for tool use, thanks

sorry forgot the setting

I don't use LMstudio, but read their docs about turning on/off reasoning

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment

🚀 Starting Agent Loop Tool Efficiency Test

📈 Agent Test Results

📋 Test Case Results:

Test Case: zero_general_question Status: ✅ PASSED Matched Path: no_tools Response Time: 7.1037635s Tool Calls: 0

Test Case: zero_greeting Status: ✅ PASSED Matched Path: no_tools Response Time: 7.6242963s Tool Calls: 0

Test Case: zero_thank_you Status: ✅ PASSED Matched Path: no_tools Response Time: 8.6742927s Tool Calls: 0

Test Case: zero_weather_question Status: ✅ PASSED Matched Path: no_tools Response Time: 10.222154s Tool Calls: 0

Test Case: zero_capabilities Status: ✅ PASSED Matched Path: no_tools Response Time: 10.7087085s Tool Calls: 0

Test Case: simple_view_cart Status: ✅ PASSED Matched Path: view_cart Response Time: 11.081606s Tool Calls: 1 Tools Used: view_cart

Test Case: simple_remove_product Status: ✅ PASSED Matched Path: direct_remove Response Time: 14.1713419s Tool Calls: 1 Tools Used: remove_from_cart

Test Case: simple_checkout Status: ✅ PASSED Matched Path: direct_checkout Response Time: 16.2663444s Tool Calls: 1 Tools Used: checkout

Test Case: simple_add_iphone Status: ✅ PASSED Matched Path: direct_add Response Time: 16.8710434s Tool Calls: 1 Tools Used: add_to_cart

Test Case: simple_search_electronics Status: ✅ PASSED Matched Path: search_by_category Response Time: 18.9555705s Tool Calls: 1 Tools Used: search_products

Test Case: medium_search_and_add Status: ✅ PASSED Matched Path: search_by_query Response Time: 20.6402634s Tool Calls: 2 Tools Used: search_products, add_to_cart

Test Case: medium_remove_and_add Status: ✅ PASSED Matched Path: remove_then_add Response Time: 21.4799744s Tool Calls: 2 Tools Used: remove_from_cart, add_to_cart

Test Case: medium_search_category_and_add Status: ✅ PASSED Matched Path: search_then_add Response Time: 23.1171036s Tool Calls: 2 Tools Used: search_products, add_to_cart

Test Case: complex_gift_shopping Status: ✅ PASSED Matched Path: gift_shopping_workflow Response Time: 24.8069479s Tool Calls: 5 Tools Used: search_products, add_to_cart, search_products, add_to_cart, view_cart

Test Case: medium_view_and_add Status: ✅ PASSED Matched Path: view_then_add Response Time: 26.8041455s Tool Calls: 2 Tools Used: view_cart, add_to_cart

Test Case: complex_shopping_workflow Status: ❌ FAILED Response Time: 28.7320275s Tool Calls: 5 Tools Used: search_products, add_to_cart, add_to_cart, add_to_cart, checkout

Test Case: complex_cart_management Status: ✅ PASSED Matched Path: cart_organization Response Time: 29.617127s Tool Calls: 3 Tools Used: view_cart, remove_from_cart, add_to_cart

❌ Failed Tests Details:

Q5_K_P // 60 tokens/s on RTX 3060 12GB (reasoning OFF)

Q5_K_P // 60 tokens/s on RTX 3060 12GB (reasoning ON)

Test Case: zero_general_question
Status: ✅ PASSED
Matched Path: no_tools
Response Time: 7.1037635s
Tool Calls: 0

Test Case: zero_greeting
Status: ✅ PASSED
Matched Path: no_tools
Response Time: 7.6242963s
Tool Calls: 0

Test Case: zero_thank_you
Status: ✅ PASSED
Matched Path: no_tools
Response Time: 8.6742927s
Tool Calls: 0

Test Case: zero_weather_question
Status: ✅ PASSED
Matched Path: no_tools
Response Time: 10.222154s
Tool Calls: 0

Test Case: zero_capabilities
Status: ✅ PASSED
Matched Path: no_tools
Response Time: 10.7087085s
Tool Calls: 0

Test Case: simple_view_cart
Status: ✅ PASSED
Matched Path: view_cart
Response Time: 11.081606s
Tool Calls: 1
Tools Used: view_cart

Test Case: simple_remove_product
Status: ✅ PASSED
Matched Path: direct_remove
Response Time: 14.1713419s
Tool Calls: 1
Tools Used: remove_from_cart

Test Case: simple_checkout
Status: ✅ PASSED
Matched Path: direct_checkout
Response Time: 16.2663444s
Tool Calls: 1
Tools Used: checkout

Test Case: simple_add_iphone
Status: ✅ PASSED
Matched Path: direct_add
Response Time: 16.8710434s
Tool Calls: 1
Tools Used: add_to_cart

Test Case: simple_search_electronics
Status: ✅ PASSED
Matched Path: search_by_category
Response Time: 18.9555705s
Tool Calls: 1
Tools Used: search_products

Test Case: medium_search_and_add
Status: ✅ PASSED
Matched Path: search_by_query
Response Time: 20.6402634s
Tool Calls: 2
Tools Used: search_products, add_to_cart

Test Case: medium_remove_and_add
Status: ✅ PASSED
Matched Path: remove_then_add
Response Time: 21.4799744s
Tool Calls: 2
Tools Used: remove_from_cart, add_to_cart

Test Case: medium_search_category_and_add
Status: ✅ PASSED
Matched Path: search_then_add
Response Time: 23.1171036s
Tool Calls: 2
Tools Used: search_products, add_to_cart

Test Case: complex_gift_shopping
Status: ✅ PASSED
Matched Path: gift_shopping_workflow
Response Time: 24.8069479s
Tool Calls: 5
Tools Used: search_products, add_to_cart, search_products, add_to_cart, view_cart

Test Case: medium_view_and_add
Status: ✅ PASSED
Matched Path: view_then_add
Response Time: 26.8041455s
Tool Calls: 2
Tools Used: view_cart, add_to_cart

Test Case: complex_shopping_workflow
Status: ❌ FAILED
Response Time: 28.7320275s
Tool Calls: 5
Tools Used: search_products, add_to_cart, add_to_cart, add_to_cart, checkout

Test Case: complex_cart_management
Status: ✅ PASSED
Matched Path: cart_organization
Response Time: 29.617127s
Tool Calls: 3
Tools Used: view_cart, remove_from_cart, add_to_cart