Instructions to use prithivMLmods/MiniMax-H3-Image-PE-NVFP4-MTP-Repacked with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use prithivMLmods/MiniMax-H3-Image-PE-NVFP4-MTP-Repacked with Transformers:

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

pipe = pipeline("image-text-to-text", model="prithivMLmods/MiniMax-H3-Image-PE-NVFP4-MTP-Repacked")
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("prithivMLmods/MiniMax-H3-Image-PE-NVFP4-MTP-Repacked")
model = AutoModelForMultimodalLM.from_pretrained("prithivMLmods/MiniMax-H3-Image-PE-NVFP4-MTP-Repacked", 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 prithivMLmods/MiniMax-H3-Image-PE-NVFP4-MTP-Repacked with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "prithivMLmods/MiniMax-H3-Image-PE-NVFP4-MTP-Repacked"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "prithivMLmods/MiniMax-H3-Image-PE-NVFP4-MTP-Repacked",
		"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/prithivMLmods/MiniMax-H3-Image-PE-NVFP4-MTP-Repacked

SGLang

How to use prithivMLmods/MiniMax-H3-Image-PE-NVFP4-MTP-Repacked 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 "prithivMLmods/MiniMax-H3-Image-PE-NVFP4-MTP-Repacked" \
    --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": "prithivMLmods/MiniMax-H3-Image-PE-NVFP4-MTP-Repacked",
		"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 "prithivMLmods/MiniMax-H3-Image-PE-NVFP4-MTP-Repacked" \
        --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": "prithivMLmods/MiniMax-H3-Image-PE-NVFP4-MTP-Repacked",
		"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 prithivMLmods/MiniMax-H3-Image-PE-NVFP4-MTP-Repacked with Docker Model Runner:
```
docker model run hf.co/prithivMLmods/MiniMax-H3-Image-PE-NVFP4-MTP-Repacked
```

MiniMax-H3-Image-PE-NVFP4-MTP-Repacked

MiniMax-H3-Image-PE is MiniMax's prompt-expansion model for its MiniMax-H3-Image image generator. It is fine-tuned from Qwen3.8-27B and released in FP4. It turns a short request into a detailed image description and recommends an aspect ratio, returned as JSON with expanded_caption and aspect_ratio, with the output constrained to a schema by XGrammar. It runs with thinking on by default (reasoning_effort xhigh, 4,096 max tokens including reasoning), and the reasoning is returned separately. The weights cover text-to-image expansion. For image editing, the release provides only a task prompt and a message-assembly example for a vision-language model of your choice, and the card says editing support is still under development. In editing mode the model describes what is preserved and changed and returns a target_aspect_ratio. It can be served with SGLang (0.5.23 or later) or run locally through the Modular Diffusers blocks, where the FP4 weights use about 19 GiB of GPU memory. The Diffusers path runs activations in bf16, so its outputs differ slightly from the SGLang deployment. The card gives no benchmarks. The license is the MiniMax-H3-Image Community License Agreement, not Apache 2.0, and some uses need separate written authorization from MiniMax. The Qwen3.8-27B base is Apache 2.0.

MTP — Speculative Decoding: Yes | GGUF Available Here — MiniMax-H3-Image-PE-NVFP4-MTP(GGUF)

MTP-Repacked [Transformers, BF16 • U8] [NVFP4]

File Name	File Type	File Size	File Link	Description
chat_template.jinja	Jinja Template	8.95 kB	Link	Chat template for formatting conversations and prompts.
config.json	JSON	37.6 kB	Link	Core model architecture and configuration parameters.
generation_config.json	JSON	306 Bytes	Link	Default text generation parameters (e.g., temperature, top_p).
hf_quant_config.json	JSON	9.97 kB	Link	Configuration file detailing the applied quantization (e.g., NVFP4) parameters.
model-00001-of-00004.safetensors	Safetensors	5.19 GB	Link	Model weight shard 1/4. Required to load the model.
model-00002-of-00004.safetensors	Safetensors	5.2 GB	Link	Model weight shard 2/4. Required to load the model.
model-00003-of-00004.safetensors	Safetensors	5.17 GB	Link	Model weight shard 3/4. Required to load the model.
model-00004-of-00004.safetensors	Safetensors	3.21 GB	Link	Model weight shard 4/4. Required to load the model.
model.safetensors.index.json	JSON	238 kB	Link	Index file mapping model weights to their respective shards.
processor_config.json	JSON	1.19 kB	Link	Configuration for the multimodal processor (text + vision/image).
requirements.txt	Text	31 Bytes	Link	List of Python dependencies required to run or load the model.
tokenizer.json	JSON	20 MB	Link	Complete tokenizer vocabulary and encoding rules.
tokenizer_config.json	JSON	1.12 kB	Link	Tokenizer-specific configuration parameters.