Instructions to use ArnavKewalram/gemma-4-E2B-coder-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ArnavKewalram/gemma-4-E2B-coder-v1 with Transformers:

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

pipe = pipeline("text-generation", model="ArnavKewalram/gemma-4-E2B-coder-v1")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("ArnavKewalram/gemma-4-E2B-coder-v1")
model = AutoModelForMultimodalLM.from_pretrained("ArnavKewalram/gemma-4-E2B-coder-v1")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

llama-cpp-python

How to use ArnavKewalram/gemma-4-E2B-coder-v1 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="ArnavKewalram/gemma-4-E2B-coder-v1",
	filename="gemma-4-E2B-coder-v1-F16.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use ArnavKewalram/gemma-4-E2B-coder-v1 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 ArnavKewalram/gemma-4-E2B-coder-v1:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ArnavKewalram/gemma-4-E2B-coder-v1:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ArnavKewalram/gemma-4-E2B-coder-v1:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ArnavKewalram/gemma-4-E2B-coder-v1: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 ArnavKewalram/gemma-4-E2B-coder-v1:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf ArnavKewalram/gemma-4-E2B-coder-v1: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 ArnavKewalram/gemma-4-E2B-coder-v1:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ArnavKewalram/gemma-4-E2B-coder-v1:Q4_K_M

Use Docker

docker model run hf.co/ArnavKewalram/gemma-4-E2B-coder-v1:Q4_K_M

LM Studio
Jan

vLLM

How to use ArnavKewalram/gemma-4-E2B-coder-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ArnavKewalram/gemma-4-E2B-coder-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ArnavKewalram/gemma-4-E2B-coder-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ArnavKewalram/gemma-4-E2B-coder-v1:Q4_K_M

SGLang

How to use ArnavKewalram/gemma-4-E2B-coder-v1 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 "ArnavKewalram/gemma-4-E2B-coder-v1" \
    --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": "ArnavKewalram/gemma-4-E2B-coder-v1",
		"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 "ArnavKewalram/gemma-4-E2B-coder-v1" \
        --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": "ArnavKewalram/gemma-4-E2B-coder-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use ArnavKewalram/gemma-4-E2B-coder-v1 with Ollama:
```
ollama run hf.co/ArnavKewalram/gemma-4-E2B-coder-v1:Q4_K_M
```

Unsloth Studio

How to use ArnavKewalram/gemma-4-E2B-coder-v1 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 ArnavKewalram/gemma-4-E2B-coder-v1 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 ArnavKewalram/gemma-4-E2B-coder-v1 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ArnavKewalram/gemma-4-E2B-coder-v1 to start chatting

How to use ArnavKewalram/gemma-4-E2B-coder-v1 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ArnavKewalram/gemma-4-E2B-coder-v1: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": "ArnavKewalram/gemma-4-E2B-coder-v1:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use ArnavKewalram/gemma-4-E2B-coder-v1 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ArnavKewalram/gemma-4-E2B-coder-v1: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 ArnavKewalram/gemma-4-E2B-coder-v1:Q4_K_M

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use ArnavKewalram/gemma-4-E2B-coder-v1 with Docker Model Runner:
```
docker model run hf.co/ArnavKewalram/gemma-4-E2B-coder-v1:Q4_K_M
```

Lemonade

How to use ArnavKewalram/gemma-4-E2B-coder-v1 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ArnavKewalram/gemma-4-E2B-coder-v1:Q4_K_M

Run and chat with the model

lemonade run user.gemma-4-E2B-coder-v1-Q4_K_M

List all available models

lemonade list

Model intro + feedback thread

by ArnavKewalram - opened 12 days ago

Discussion

ArnavKewalram

Owner 12 days ago

Introduction

gemma-4-E2B-coder-v1 is the first coding fine-tune of google/gemma-4-E2B-it ? Google's 3.9B hybrid Griffin model (alternating attention + linear recurrent layers).

Why this model?

Most small coding models target Llama or Mistral architectures. Gemma 4 E2B is different:

Griffin architecture: faster CPU inference than pure-transformer models of the same size
Compact size: ~3.2 GB at Q4_K_M ? fits on a Raspberry Pi 5 with enough swap
Apache 2.0: commercial use without restrictions

Training

Trained on 10,000 samples from Magicoder-OSS-Instruct-75K ? real GitHub code instruction pairs ? using QLoRA on a single RTX 3080, in ~6 hours.

Eval (keyword score, Q4_K_M, 8 tasks): 88.5% average across Python, JS, Go, Rust, SQL, Bash, C++.

Try it

Live demo ? runs on ZeroGPU, no setup needed
Ollama: ollama run hf.co/ArnavKewalram/gemma-4-E2B-coder-v1:Q4_K_M
Colab notebook: linked in the model card

Feedback welcome

If you try this model, I'd love to know:

What languages / tasks work well vs. where it struggles?
Does it perform better or worse than other ~4B coders you've tried?

Known limitations: training max was 384 tokens, so very long prompts may produce truncated or lower-quality output.

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