Instructions to use iamlyth/gemma4-e4b-ha with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use iamlyth/gemma4-e4b-ha with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("unsloth/gemma-4-E4B-it")
model = PeftModel.from_pretrained(base_model, "iamlyth/gemma4-e4b-ha")

Transformers

How to use iamlyth/gemma4-e4b-ha with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="iamlyth/gemma4-e4b-ha")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("iamlyth/gemma4-e4b-ha", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use iamlyth/gemma4-e4b-ha 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 iamlyth/gemma4-e4b-ha:Q4_K_S
# Run inference directly in the terminal:
llama cli -hf iamlyth/gemma4-e4b-ha:Q4_K_S

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf iamlyth/gemma4-e4b-ha:Q4_K_S
# Run inference directly in the terminal:
llama cli -hf iamlyth/gemma4-e4b-ha:Q4_K_S

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 iamlyth/gemma4-e4b-ha:Q4_K_S
# Run inference directly in the terminal:
./llama-cli -hf iamlyth/gemma4-e4b-ha:Q4_K_S

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 iamlyth/gemma4-e4b-ha:Q4_K_S
# Run inference directly in the terminal:
./build/bin/llama-cli -hf iamlyth/gemma4-e4b-ha:Q4_K_S

Use Docker

docker model run hf.co/iamlyth/gemma4-e4b-ha:Q4_K_S

LM Studio
Jan

vLLM

How to use iamlyth/gemma4-e4b-ha with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "iamlyth/gemma4-e4b-ha"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "iamlyth/gemma4-e4b-ha",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/iamlyth/gemma4-e4b-ha:Q4_K_S

SGLang

How to use iamlyth/gemma4-e4b-ha with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "iamlyth/gemma4-e4b-ha" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "iamlyth/gemma4-e4b-ha",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "iamlyth/gemma4-e4b-ha" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "iamlyth/gemma4-e4b-ha",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use iamlyth/gemma4-e4b-ha with Ollama:
```
ollama run hf.co/iamlyth/gemma4-e4b-ha:Q4_K_S
```
Unsloth Desktop

How to use iamlyth/gemma4-e4b-ha with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf iamlyth/gemma4-e4b-ha:Q4_K_S

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": "iamlyth/gemma4-e4b-ha:Q4_K_S"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use iamlyth/gemma4-e4b-ha with Docker Model Runner:
```
docker model run hf.co/iamlyth/gemma4-e4b-ha:Q4_K_S
```

Lemonade

How to use iamlyth/gemma4-e4b-ha with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull iamlyth/gemma4-e4b-ha:Q4_K_S

Run and chat with the model

lemonade run user.gemma4-e4b-ha-Q4_K_S

List all available models

lemonade list

Hermes Agent

How to use iamlyth/gemma4-e4b-ha with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf iamlyth/gemma4-e4b-ha:Q4_K_S

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 iamlyth/gemma4-e4b-ha:Q4_K_S

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use iamlyth/gemma4-e4b-ha with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf iamlyth/gemma4-e4b-ha:Q4_K_S

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 "iamlyth/gemma4-e4b-ha:Q4_K_S" \
  --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"

Model Card for gemma4-e4b-ha

This model is a fine-tuned version of unsloth/gemma-4-E4B-it. It has been trained using TRL and trained on the acon96 Home Assistant V2 Training Set. Optimized to make home assistant tool calls targeted for the nVidia Jetson Nano devices.

Quick start

from transformers import pipeline

question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="None", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])

Training procedure

This model was trained with SFT.

Framework versions

PEFT 0.19.1
TRL: 0.24.0
Transformers: 5.5.0
Pytorch: 2.10.0
Datasets: 4.3.0
Tokenizers: 0.22.2

Citations

Cite TRL as:

@misc{vonwerra2022trl,
    title        = {{TRL: Transformer Reinforcement Learning}},
    author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
    year         = 2020,
    journal      = {GitHub repository},
    publisher    = {GitHub},
    howpublished = {\url{https://github.com/huggingface/trl}}
}

Downloads last month: 37

GGUF

Model size

8B params

Architecture

gemma4

Hardware compatibility

4-bit

Model tree for iamlyth/gemma4-e4b-ha

Base model

google/gemma-4-E4B

Finetuned

google/gemma-4-E4B-it

Finetuned

unsloth/gemma-4-E4B-it

Adapter

(68)

this model