Instructions to use google/gemma-4-26B-A4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use google/gemma-4-26B-A4B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="google/gemma-4-26B-A4B")# Load model directly from transformers import AutoProcessor, AutoModelForImageTextToText processor = AutoProcessor.from_pretrained("google/gemma-4-26B-A4B") model = AutoModelForImageTextToText.from_pretrained("google/gemma-4-26B-A4B") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use google/gemma-4-26B-A4B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "google/gemma-4-26B-A4B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "google/gemma-4-26B-A4B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/google/gemma-4-26B-A4B
- SGLang
How to use google/gemma-4-26B-A4B 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 "google/gemma-4-26B-A4B" \ --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": "google/gemma-4-26B-A4B", "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 "google/gemma-4-26B-A4B" \ --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": "google/gemma-4-26B-A4B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use google/gemma-4-26B-A4B with Docker Model Runner:
docker model run hf.co/google/gemma-4-26B-A4B
Please, release 8B - 12B version
#9 opened 11 days ago
by
AlxHQ
rabbit-software
1
#8 opened about 1 month ago
by
Therealsickonechase-bit
LiteRT models?
#7 opened about 1 month ago
by
rnett3
Community resources for Gemma 4 deployment β mobile, local, and cloud paths
π 1
2
#6 opened about 1 month ago
by
Linncharm
QAT-IT models
π 5
4
#5 opened about 2 months ago
by
TheChola
please fp8
π 2
1
#4 opened about 2 months ago
by
huang123chuan
Upload tokenizer
1
#3 opened about 2 months ago
by
ArthurZ