Instructions to use retowyss/gemma-4-26B-A4B-it-REAP2D with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use retowyss/gemma-4-26B-A4B-it-REAP2D with Transformers:

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

pipe = pipeline("text-generation", model="retowyss/gemma-4-26B-A4B-it-REAP2D")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("retowyss/gemma-4-26B-A4B-it-REAP2D")
model = AutoModelForMultimodalLM.from_pretrained("retowyss/gemma-4-26B-A4B-it-REAP2D", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use retowyss/gemma-4-26B-A4B-it-REAP2D with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "retowyss/gemma-4-26B-A4B-it-REAP2D"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "retowyss/gemma-4-26B-A4B-it-REAP2D",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/retowyss/gemma-4-26B-A4B-it-REAP2D

SGLang

How to use retowyss/gemma-4-26B-A4B-it-REAP2D 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 "retowyss/gemma-4-26B-A4B-it-REAP2D" \
    --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": "retowyss/gemma-4-26B-A4B-it-REAP2D",
		"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 "retowyss/gemma-4-26B-A4B-it-REAP2D" \
        --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": "retowyss/gemma-4-26B-A4B-it-REAP2D",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use retowyss/gemma-4-26B-A4B-it-REAP2D with Docker Model Runner:
```
docker model run hf.co/retowyss/gemma-4-26B-A4B-it-REAP2D
```

Gemma-4-26B-A4B REAP to Dense

A one-shot expert-pruned version of google/gemma-4-26B-A4B-it, produced with the REAP (Router-weighted Expert Activation Pruning) pipeline as a ~4B dense conversion of the original 26B MoE.

Each layer keeps only the K = k = 8 most-salient experts exactly matching top_k_experts. So, every token is routed through all retained experts every time. The sparse routing degenerates into a dense FFN.

	Original	Pruned (this)
Parameters (text MoE)	25.2B	4.39B
Experts per layer	128	8
Active per token	8	8
Weight size (bf16)	~50 GB	8.2 GB
Compression	—	93.75% expert reduction

The dense MLP block already present in each Gemma 4 layer is retained and its output is still summed with the MoE path, as in the original architecture.

Base: google/gemma-4-26B-A4B-it
Method: REAP (Router-weighted Expert Activation Pruning), layerwise error-accumulation calibration

Caveats

It is intended as a research start point (e.g. via logit distillation)
Vision tower and embeddings are unchanged from the original.

License

Apache 2.0, per the original Gemma 4 license. See license_link.

Downloads last month: 38

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for retowyss/gemma-4-26B-A4B-it-REAP2D

Base model

google/gemma-4-26B-A4B

Finetuned

google/gemma-4-26B-A4B-it

Finetuned

(195)

this model

retowyss
/

gemma-4-26B-A4B-it-REAP2D

Gemma-4-26B-A4B REAP to Dense

Caveats

License

Model tree for retowyss/gemma-4-26B-A4B-it-REAP2D

Dataset used to train retowyss/gemma-4-26B-A4B-it-REAP2D