Instructions to use INCModelSharing/MiniMax-M3-MXFP4-Mixed-CT-AutoRound-Tuning with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use INCModelSharing/MiniMax-M3-MXFP4-Mixed-CT-AutoRound-Tuning with Transformers:

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

pipe = pipeline("image-text-to-text", model="INCModelSharing/MiniMax-M3-MXFP4-Mixed-CT-AutoRound-Tuning", trust_remote_code=True)
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("INCModelSharing/MiniMax-M3-MXFP4-Mixed-CT-AutoRound-Tuning", trust_remote_code=True)
model = AutoModelForMultimodalLM.from_pretrained("INCModelSharing/MiniMax-M3-MXFP4-Mixed-CT-AutoRound-Tuning", trust_remote_code=True, 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 INCModelSharing/MiniMax-M3-MXFP4-Mixed-CT-AutoRound-Tuning with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "INCModelSharing/MiniMax-M3-MXFP4-Mixed-CT-AutoRound-Tuning"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "INCModelSharing/MiniMax-M3-MXFP4-Mixed-CT-AutoRound-Tuning",
		"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/INCModelSharing/MiniMax-M3-MXFP4-Mixed-CT-AutoRound-Tuning

SGLang

How to use INCModelSharing/MiniMax-M3-MXFP4-Mixed-CT-AutoRound-Tuning 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 "INCModelSharing/MiniMax-M3-MXFP4-Mixed-CT-AutoRound-Tuning" \
    --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": "INCModelSharing/MiniMax-M3-MXFP4-Mixed-CT-AutoRound-Tuning",
		"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 "INCModelSharing/MiniMax-M3-MXFP4-Mixed-CT-AutoRound-Tuning" \
        --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": "INCModelSharing/MiniMax-M3-MXFP4-Mixed-CT-AutoRound-Tuning",
		"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 INCModelSharing/MiniMax-M3-MXFP4-Mixed-CT-AutoRound-Tuning with Docker Model Runner:
```
docker model run hf.co/INCModelSharing/MiniMax-M3-MXFP4-Mixed-CT-AutoRound-Tuning
```

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

This model is a MXFP4 mixed model of MiniMax-M3 tuned by intel/auto-round with llm_compressor format. Please follow the license of the original model.

MOE (block_sparse_moe.experts): MXFP4
MOE (block_sparse_moe.shared_experts): MXFP8

Configuration	GPQA Diamond	AIME 2026	SWE-Bench Mini
BF16	0.9242	0.9000	0.70
MXFP8	0.9242	0.9333	0.68
MXFP4 (Experts) + MXFP8 (Shared Experts)	0.9444	0.9667	0.74

The MXFP8 baseline model is from MiniMaxAI/MiniMax-M3-MXFP8)
SWE-Bench Mini is evaluated using MariusHobbhahn/swe-bench-verified-mini. SWE-Bench Verified Mini is a compact subset of SWE-Bench Verified containing 50 carefully selected instances. It preserves the performance distribution, pass rate, and difficulty characteristics of the full SWE-Bench Verified benchmark while requiring only approximately 5 GB of storage, compared to roughly 130 GB for the full dataset.
GPQA Diamond and AIME 2026 evaluations are conducted using EvalScope

How to Run Locally

vllm serve \
  INCModelSharing/MiniMax-M3-MXFP4-Mixed-CT-AutoRound-Tuning \
  --tensor-parallel-size 2 \
  --max-model-len 131072 \
  --tool-call-parser minimax_m3 \
  --reasoning-parser minimax_m3 \
  --enable-auto-tool-choice \
  --port 8000

curl -s http://127.0.0.1:8000/v1/chat/completions   -H "Content-Type: application/json"   -d '{
    "model": "INCModelSharing/MiniMax-M3-MXFP4-Mixed-CT-AutoRound-Tuning",
    "messages": [
      {"role":"user","content":"2+3=?"}
    ],
    "max_tokens": 10,
    "extra_body": {
      "chat_template_kwargs": {
        "enable_thinking": true
      }
    }
  }' | python3 -m json.tool

Generate the Model

auto-round ../MiniMax-M3/ \
  --iters 200 \
  --scheme MXFP8 \
  --ignore_layers "vision_tower,lm_head,block_sparse_moe.gate,\
embed_tokens,self_attn,patch_merge_mlp,multi_modal_projector,\
mlp.gate_up_proj,mlp.down_proj" \
  --layer_config '{mlp.experts:{bits:4,data_type:mx_fp}}' \
  --format llm_compressor \
  --output_dir ./MiniMax-M3-MXFP4MoE-MXFP8-tuning200 \
  --device_map auto

Ethical Considerations and Limitations

The model can produce factually incorrect output, and should not be relied on to produce factually accurate information. Because of the limitations of the pretrained model and the finetuning datasets, it is possible that this model could generate lewd, biased or otherwise offensive outputs.

Therefore, before deploying any applications of the model, developers should perform safety testing.

Caveats and Recommendations

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model.

Here are a couple of useful links to learn more about Intel's AI software:

Intel Neural Compressor

Disclaimer

The license on this model does not constitute legal advice. We are not responsible for the actions of third parties who use this model. Please consult an attorney before using this model for commercial purposes.

Cite

@article{cheng2023optimize, title={Optimize weight rounding via signed gradient descent for the quantization of llms}, author={Cheng, Wenhua and Zhang, Weiwei and Shen, Haihao and Cai, Yiyang and He, Xin and Lv, Kaokao and Liu, Yi}, journal={arXiv preprint arXiv:2309.05516}, year={2023} }

arxiv github

Downloads last month: -

Safetensors

Model size

233B params

Tensor type

BF16

F8_E4M3

Paper for INCModelSharing/MiniMax-M3-MXFP4-Mixed-CT-AutoRound-Tuning

Optimize Weight Rounding via Signed Gradient Descent for the Quantization of LLMs

Paper • 2309.05516 • Published Sep 11, 2023 • 13