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

Libraries

How to use unsloth/gemma-4-E4B-it-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="unsloth/gemma-4-E4B-it-GGUF",
	filename="MTP/mtp-gemma-4-E4B-it-BF16.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 unsloth/gemma-4-E4B-it-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 unsloth/gemma-4-E4B-it-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf unsloth/gemma-4-E4B-it-GGUF:UD-Q4_K_XL

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf unsloth/gemma-4-E4B-it-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf unsloth/gemma-4-E4B-it-GGUF:UD-Q4_K_XL

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 unsloth/gemma-4-E4B-it-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./llama-cli -hf unsloth/gemma-4-E4B-it-GGUF:UD-Q4_K_XL

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 unsloth/gemma-4-E4B-it-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf unsloth/gemma-4-E4B-it-GGUF:UD-Q4_K_XL

Use Docker

docker model run hf.co/unsloth/gemma-4-E4B-it-GGUF:UD-Q4_K_XL

LM Studio
Jan

vLLM

How to use unsloth/gemma-4-E4B-it-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "unsloth/gemma-4-E4B-it-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": "unsloth/gemma-4-E4B-it-GGUF",
		"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/unsloth/gemma-4-E4B-it-GGUF:UD-Q4_K_XL

Ollama
How to use unsloth/gemma-4-E4B-it-GGUF with Ollama:
```
ollama run hf.co/unsloth/gemma-4-E4B-it-GGUF:UD-Q4_K_XL
```

Unsloth Studio

How to use unsloth/gemma-4-E4B-it-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 unsloth/gemma-4-E4B-it-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 unsloth/gemma-4-E4B-it-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for unsloth/gemma-4-E4B-it-GGUF to start chatting

How to use unsloth/gemma-4-E4B-it-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf unsloth/gemma-4-E4B-it-GGUF:UD-Q4_K_XL

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": "unsloth/gemma-4-E4B-it-GGUF:UD-Q4_K_XL"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use unsloth/gemma-4-E4B-it-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 unsloth/gemma-4-E4B-it-GGUF:UD-Q4_K_XL

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 unsloth/gemma-4-E4B-it-GGUF:UD-Q4_K_XL

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use unsloth/gemma-4-E4B-it-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf unsloth/gemma-4-E4B-it-GGUF:UD-Q4_K_XL

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 "unsloth/gemma-4-E4B-it-GGUF:UD-Q4_K_XL" \
  --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"

Docker Model Runner
How to use unsloth/gemma-4-E4B-it-GGUF with Docker Model Runner:
```
docker model run hf.co/unsloth/gemma-4-E4B-it-GGUF:UD-Q4_K_XL
```

Lemonade

How to use unsloth/gemma-4-E4B-it-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull unsloth/gemma-4-E4B-it-GGUF:UD-Q4_K_XL

Run and chat with the model

lemonade run user.gemma-4-E4B-it-GGUF-UD-Q4_K_XL

List all available models

lemonade list

Why are all small models so bad for me, doing something wrong?

#17

by Xhatz - opened May 31

Discussion

Xhatz

May 31

ALL models I've tried without exception are quite useless, either just doing very bad, creating files I ask for twice, looping on useless commands, or saying nonsense, or, for this one, it just says it will do thing and does not actually do things, just yapping a lot! I'm using LM Studio with nanobot... I didn't have problems with models like MiniMax, I just wanted to try small ones, but I don't know if they're all really stupid or if I'm doing something very wrong lol. Thank you for your responses and help!

JeanJan90

Jun 3

ALL models I've tried without exception are quite useless, either just doing very bad, creating files I ask for twice, looping on useless commands, or saying nonsense, or, for this one, it just says it will do thing and does not actually do things, just yapping a lot! I'm using LM Studio with nanobot... I didn't have problems with models like MiniMax, I just wanted to try small ones, but I don't know if they're all really stupid or if I'm doing something very wrong lol. Thank you for your responses and help!

of all the AI i tested this model here Gemma 4 e4b is the best and does not loop literally and You cant lie that this one loops cause this thing literally does not i have tested it, Qwen on the other hand all param are the loopers and dogshit gemma here is innocent either you are using the most unhinged Q2 or Q3 or i dont know maybe your PC is haunted or something even on Q2 and Q3 i cant replicate the looping on this gemma 4 e4b thats how weirdly high quality this thing is.

as far I can tell with your issue, try checking your Chat template and nucleus settings and for the love of God pls check if you are on the latest engine or inference form ollama or kobold or LM studio etc that actually supports Gemma 4.

Xhatz

Jun 3

•

edited Jun 3

As far as I know I did was on the latest versions, I even redownloaded koboldcpp, lm studio and ollama to try, but yeah it's just so unreliable for tool tasks. For me for example, I had asked it to edit a single line in a file, and it kept trying to edit the same file over and over and destroying the formatting inside lol, I don't know what I was doing wrong, I had set the temp and other parameters to the recommended ones, used last versions of software, q8, but nothing really fixed it

Even the new gemma4 12b just loops on a new session, running the same commands to find a file and outputting the exact same messages...
I simply ask "try to run this program on my windows computer", and it goes
┊ 🔎 preparing search_files…
┊ 🔎 find prism 0.1s
┊ 🔎 preparing search_files…
┊ 🔎 find prism 0.1s
┊ 🔎 preparing search_files…
┊ 🔎 find prism 0.1s
┊ 🔎 preparing search_files…
┊ 🔎 find prism 0.1s
┊ 🔎 preparing search_files…
┊ 🔎 find prism 0.1s
┊ 🔎 preparing search_files…
┊ 🔎 find prism 0.1s
it does this with every gemma4 model for me :(

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