Instructions to use z-lab/gemma-4-26B-A4B-it-DFlash with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use z-lab/gemma-4-26B-A4B-it-DFlash with Transformers:

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

pipe = pipeline("text-generation", model="z-lab/gemma-4-26B-A4B-it-DFlash")

# Load model directly
from transformers import AutoTokenizer, AutoModel

tokenizer = AutoTokenizer.from_pretrained("z-lab/gemma-4-26B-A4B-it-DFlash")
model = AutoModel.from_pretrained("z-lab/gemma-4-26B-A4B-it-DFlash")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use z-lab/gemma-4-26B-A4B-it-DFlash with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "z-lab/gemma-4-26B-A4B-it-DFlash"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "z-lab/gemma-4-26B-A4B-it-DFlash",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/z-lab/gemma-4-26B-A4B-it-DFlash

SGLang

How to use z-lab/gemma-4-26B-A4B-it-DFlash 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 "z-lab/gemma-4-26B-A4B-it-DFlash" \
    --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": "z-lab/gemma-4-26B-A4B-it-DFlash",
		"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 "z-lab/gemma-4-26B-A4B-it-DFlash" \
        --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": "z-lab/gemma-4-26B-A4B-it-DFlash",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use z-lab/gemma-4-26B-A4B-it-DFlash with Docker Model Runner:
```
docker model run hf.co/z-lab/gemma-4-26B-A4B-it-DFlash
```

Sglang support?

by Pragmatism0220 - opened 9 days ago

Discussion

Pragmatism0220

9 days ago

ValueError: Model Gemma4ForConditionalGeneration does not implement set_dflash_layers_to_capture, which is required for DFLASH.

jianchen0311

Z Lab org 9 days ago

Did you install the SGLang through uv pip install "git+https://github.com/sgl-project/sglang.git@refs/pull/23000/head#subdirectory=python"? We have updated support of DFlash in the latest commit in this PR. This PR hasn't been merged.

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