Instructions to use MRockatansky/gemma-4-31B-Mergemaxxed with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MRockatansky/gemma-4-31B-Mergemaxxed with Transformers:

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

pipe = pipeline("image-text-to-text", model="MRockatansky/gemma-4-31B-Mergemaxxed")
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)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("MRockatansky/gemma-4-31B-Mergemaxxed")
model = AutoModelForMultimodalLM.from_pretrained("MRockatansky/gemma-4-31B-Mergemaxxed", 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=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use MRockatansky/gemma-4-31B-Mergemaxxed with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MRockatansky/gemma-4-31B-Mergemaxxed"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MRockatansky/gemma-4-31B-Mergemaxxed",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/MRockatansky/gemma-4-31B-Mergemaxxed

SGLang

How to use MRockatansky/gemma-4-31B-Mergemaxxed 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 "MRockatansky/gemma-4-31B-Mergemaxxed" \
    --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": "MRockatansky/gemma-4-31B-Mergemaxxed",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "MRockatansky/gemma-4-31B-Mergemaxxed" \
        --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": "MRockatansky/gemma-4-31B-Mergemaxxed",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use MRockatansky/gemma-4-31B-Mergemaxxed with Docker Model Runner:
```
docker model run hf.co/MRockatansky/gemma-4-31B-Mergemaxxed
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Mergemaxxed

Yet another Gemma-4 merge. I decided to try merge some new models to Storymaxxed. Zerofata's excellent MeroMero which has great style and makes for fun roleplays and Pantheon which hones Gemma-4's reasoning traces. Both models really bolster Storymaxxed and this one really shines with fun dialogue, creative narratives, and strong instruction following capability.

Merge Details

Merge Method

This model was merged using the DARE TIES merge method using MRockatansky/Gemma-4-31B-storymaxxed2 as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

# Model Merge Configuration for Creative Writing & Roleplay Gemma-4
# Combines: Storymaxxed (story writing), MeroMero (roleplay), Pantheon (reasoning)
# Merge Method: DARE TIES - Best for 3+ specialized models with distinct capabilities

merge_method: dare_ties

base_model: MRockatansky/Gemma-4-31B-storymaxxed2  # Using Storymaxxed as base

models:
  # Primary: Story Writing Specialist
  - model: MRockatansky/Gemma-4-31B-storymaxxed2
    parameters:
      weight: 0.4
      density: 0.7  # Keep 70% of task vector parameters

  # Secondary: Creative Roleplay Specialist  
  - model: zerofata/G4-MeroMero-31B
    parameters:
      weight: 0.3
      density: 0.7  # Keep 70% of task vector parameters

  # Tertiary: Reasoning Enhancement
  - model: Gryphe/Pantheon-Reasoning-31B-1.1
    parameters:
      weight: 0.3
      density: 0.7  # Keep 70% of task vector parameters

parameters:
  # Normalize weights across models
  normalize: true
  
  # Use int8 masks for memory efficiency (important for 31B models)
  int8_mask: true

# Output precision - bfloat16 recommended for Gemma-4
dtype: bfloat16

# Optional: Tokenizer configuration
# Using union to preserve any special tokens from all models
tokenizer:
  source: union