Instructions to use bunnycore/Gemma4-E2B-Coding-Distill with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bunnycore/Gemma4-E2B-Coding-Distill with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("unsloth/gemma-4-e2b-it-unsloth-bnb-4bit")
model = PeftModel.from_pretrained(base_model, "bunnycore/Gemma4-E2B-Coding-Distill")

Transformers

How to use bunnycore/Gemma4-E2B-Coding-Distill with Transformers:

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

pipe = pipeline("text-generation", model="bunnycore/Gemma4-E2B-Coding-Distill")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("bunnycore/Gemma4-E2B-Coding-Distill", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use bunnycore/Gemma4-E2B-Coding-Distill with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bunnycore/Gemma4-E2B-Coding-Distill"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bunnycore/Gemma4-E2B-Coding-Distill",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/bunnycore/Gemma4-E2B-Coding-Distill

SGLang

How to use bunnycore/Gemma4-E2B-Coding-Distill 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 "bunnycore/Gemma4-E2B-Coding-Distill" \
    --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": "bunnycore/Gemma4-E2B-Coding-Distill",
		"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 "bunnycore/Gemma4-E2B-Coding-Distill" \
        --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": "bunnycore/Gemma4-E2B-Coding-Distill",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use bunnycore/Gemma4-E2B-Coding-Distill with Docker Model Runner:
```
docker model run hf.co/bunnycore/Gemma4-E2B-Coding-Distill
```

Model Card: Gemma 4 E2B — Frontier Distilled LoRA

Overview

This repository provides a Low-Rank Adaptation (LoRA) adapter for Gemma 4 E2B. The adapter was fine-tuned on a focused dataset of several thousand high-signal instruction, reasoning, and conversational samples distilled from leading frontier models.

Model Details

Base Model: google/gemma-4-e2b (Gemma 4 E2B)
Adapter Type: LoRA (Low-Rank Adaptation)
Primary Task: Instruction following, structured reasoning, and conversational text generation
Language(s): English (primary)
License: Open weights under the Gemma Terms of Use; Apache 2.0 for custom adapter weights
PEFT 0.18.1

Downloads last month: 58

GGUF

Model size

0.1B params

Architecture

gemma4

Hardware compatibility

16-bit