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

Libraries

How to use majentik/gemma-4-26B-A4B-RotorQuant with Transformers:

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

pipe = pipeline("image-text-to-text", model="majentik/gemma-4-26B-A4B-RotorQuant")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("majentik/gemma-4-26B-A4B-RotorQuant", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use majentik/gemma-4-26B-A4B-RotorQuant with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/majentik/gemma-4-26B-A4B-RotorQuant

SGLang

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

Docker Model Runner
How to use majentik/gemma-4-26B-A4B-RotorQuant with Docker Model Runner:
```
docker model run hf.co/majentik/gemma-4-26B-A4B-RotorQuant
```

The latest "johndpope/llama-cpp-turboquant" doesn't support Gemma4

by IronKitty - opened 19 days ago

Discussion

IronKitty

19 days ago

It is seems like that the latest "johndpope/llama-cpp-turboquant" doesn't support Gemma4.

'''
Loading model... |llama_model_load: error loading model: error loading model architecture: unknown model architecture: 'gemma4'
llama_model_load_from_file_impl: failed to load model
llama_params_fit: encountered an error while trying to fit params to free device memory: failed to load model
-llama_model_load: error loading model: error loading model architecture: unknown model architecture: 'gemma4'
llama_model_load_from_file_impl: failed to load model
common_init_from_params: failed to load model './Downloads/gemma-4-26B-A4B-it-RotorQuant-IQ4_XS.gguf'
srv load_model: failed to load model, './Downloads/gemma-4-26B-A4B-it-RotorQuant-IQ4_XS.gguf'
'''

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