Instructions to use twinkle-ai/gemma-3-4B-T1-it with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use twinkle-ai/gemma-3-4B-T1-it with Transformers:

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

pipe = pipeline("text-generation", model="twinkle-ai/gemma-3-4B-T1-it")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("twinkle-ai/gemma-3-4B-T1-it")
model = AutoModelForMultimodalLM.from_pretrained("twinkle-ai/gemma-3-4B-T1-it")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use twinkle-ai/gemma-3-4B-T1-it with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "twinkle-ai/gemma-3-4B-T1-it"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "twinkle-ai/gemma-3-4B-T1-it",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/twinkle-ai/gemma-3-4B-T1-it

SGLang

How to use twinkle-ai/gemma-3-4B-T1-it 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 "twinkle-ai/gemma-3-4B-T1-it" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "twinkle-ai/gemma-3-4B-T1-it",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "twinkle-ai/gemma-3-4B-T1-it" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "twinkle-ai/gemma-3-4B-T1-it",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use twinkle-ai/gemma-3-4B-T1-it with Docker Model Runner:
```
docker model run hf.co/twinkle-ai/gemma-3-4B-T1-it
```

gemma-3-4B-T1-it / tokenizer_config.json

minyichen

Initial model upload

df28220 5 months ago

download

history blame contribute delete

1.16 MB

This file is stored with Xet . It is too big to display, but you can still download it.

Xet Pointer Details

( Raw pointer file )

Xet hash:: f2287b31f45a03d8181661b609c2408fbd843993d454daf1f492998191457ec3
Size of remote file:: 1.16 MB
SHA256:: 227c6f91376cb7b90efe1940518366797ae053737f96c2d67e30afedd4b09084

Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.