Instructions to use kenonix/gemma-3-ko-4B-1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kenonix/gemma-3-ko-4B-1 with Transformers:

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

pipe = pipeline("text-generation", model="kenonix/gemma-3-ko-4B-1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("kenonix/gemma-3-ko-4B-1")
model = AutoModelForCausalLM.from_pretrained("kenonix/gemma-3-ko-4B-1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use kenonix/gemma-3-ko-4B-1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kenonix/gemma-3-ko-4B-1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kenonix/gemma-3-ko-4B-1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/kenonix/gemma-3-ko-4B-1

SGLang

How to use kenonix/gemma-3-ko-4B-1 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 "kenonix/gemma-3-ko-4B-1" \
    --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": "kenonix/gemma-3-ko-4B-1",
		"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 "kenonix/gemma-3-ko-4B-1" \
        --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": "kenonix/gemma-3-ko-4B-1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio new

How to use kenonix/gemma-3-ko-4B-1 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 kenonix/gemma-3-ko-4B-1 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 kenonix/gemma-3-ko-4B-1 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for kenonix/gemma-3-ko-4B-1 to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="kenonix/gemma-3-ko-4B-1",
    max_seq_length=2048,
)

Docker Model Runner
How to use kenonix/gemma-3-ko-4B-1 with Docker Model Runner:
```
docker model run hf.co/kenonix/gemma-3-ko-4B-1
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

그.. 대충 해명을 하자면, 이런 vllm 모델은 처음 GRPO로 파인튜닝하는데, 왜인진 모르겠으나 이미지 인식하는 부분이 gguf로 변환하니까 안되네요. 근데 Q4_K_M으로 양자화 해놔도 한국어를 매우 잘 구사합니다. 대충 Q4_K_M 기준 vram 4.3GB 쓰네요. 대충 GGUF로 만들어 뒀으니 프롬프팅해서 쓰십쇼

Uploaded finetuned model

Developed by: kenonix
License: apache-2.0
Finetuned from model : unsloth/gemma-3-4b-it-unsloth-bnb-4bit

This gemma3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

Downloads last month: -

Model tree for kenonix/gemma-3-ko-4B-1

Base model

google/gemma-3-4b-pt

Finetuned

google/gemma-3-4b-it

Quantized

unsloth/gemma-3-4b-it-unsloth-bnb-4bit

Finetuned

(1100)

this model

Finetunes

1 model

Quantizations

3 models