Instructions to use INCModelSharing/MiniMax-M3-MXFP4-Mixed-CT-AutoRound 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 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", 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", trust_remote_code=True)
model = AutoModelForMultimodalLM.from_pretrained("INCModelSharing/MiniMax-M3-MXFP4-Mixed-CT-AutoRound", 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?"}
        ]
    },
]
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 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"
# 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",
		"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

SGLang

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

MiniMax-M3-MXFP4-Mixed-CT-AutoRound / .eval_results /minimax-m3.yaml

lvkaokao

Upload folder using huggingface_hub

70b0b84 verified 2 days ago

Raw

History Blame Contribute Delete

3.62 kB

	# Evaluation results for MiniMaxAI/MiniMax-M3
	# Extracted from the model card benchmark graph (figures/benchmark.jpeg)
	# https://huggingface.co/MiniMaxAI/MiniMax-M3
	# Paper: https://arxiv.org/abs/2606.13392

	# ---------------------------------------------------------------------------
	# Coding
	# ---------------------------------------------------------------------------

	# SWE-Bench Verified - 80.5
	- dataset:
	id: SWE-bench/SWE-bench_Verified
	task_id: swe_bench_%_resolved
	value: 80.5
	source:
	url: https://huggingface.co/MiniMaxAI/MiniMax-M3
	name: MiniMax-M3 model card
	notes: "Evaluated on internal infrastructure using Claude Code as the scaffolding. Each test was run 4 times and the average was taken."

	# SWE-Bench Pro - 59.0
	- dataset:
	id: ScaleAI/SWE-bench_Pro
	task_id: SWE_Bench_Pro
	value: 59.0
	source:
	url: https://huggingface.co/MiniMaxAI/MiniMax-M3
	name: MiniMax-M3 model card
	notes: "Evaluated on internal infrastructure using Claude Code as the scaffolding. Testing logic is aligned with the official evaluation."


	# ---------------------------------------------------------------------------
	# Multimodal
	# ---------------------------------------------------------------------------

	# MMMU-Pro - 78.1
	# MMMU-Pro defines three tasks: mmmu_pro_vision, mmmu_pro_standard_4_options,
	# mmmu_pro_standard_10_options. The model card reports a single "MMMU-Pro"
	# score without specifying the exact variant. We map it to the standard
	# 10-options task as the most common updated benchmark configuration.
	- dataset:
	id: MMMU/MMMU_Pro
	task_id: mmmu_pro_standard_10_options
	value: 78.1
	source:
	url: https://huggingface.co/MiniMaxAI/MiniMax-M3
	name: MiniMax-M3 model card
	notes: "MMMU-Pro score extracted from the model card benchmark graph. The exact task variant (vision, standard 4-options, or standard 10-options) is not explicitly stated."

	# Video-MME (w/ sub) - 85.4
	# Mapped to Video-MME-v2, the registered successor benchmark on the Hub.
	- dataset:
	id: MME-Benchmarks/Video-MME-v2
	task_id: video-mme-v2
	value: 85.4
	source:
	url: https://huggingface.co/MiniMaxAI/MiniMax-M3
	name: MiniMax-M3 model card
	notes: "Model card reports 'VideoMME (w/ sub)'. Mapped to the closest registered benchmark on the Hub, Video-MME-v2."

	# ---------------------------------------------------------------------------
	# Cowork
	# ---------------------------------------------------------------------------

	# Claw-Eval - 74.5
	# Claw-Eval defines three tasks: general, multimodal, multi_turn. The model card
	# reports a single overall score, so it is mapped to the 'general' task.
	- dataset:
	id: claw-eval/Claw-Eval
	task_id: general
	value: 74.5
	source:
	url: https://huggingface.co/MiniMaxAI/MiniMax-M3
	name: MiniMax-M3 model card
	notes: "Model card reports a single 'Claw-Eval' score. Mapped to the 'general' task (overall); the exact task split is not specified."

	# Apex-Agents - 27.7
	- dataset:
	id: mercor/apex-agents
	task_id: apex-agents
	value: 27.7
	source:
	url: https://huggingface.co/MiniMaxAI/MiniMax-M3
	name: MiniMax-M3 model card
	notes: "Evaluated on the apex-agents benchmark."

	# YC-Bench - 2.1M (final assets in fund, monetary metric)
	- dataset:
	id: collinear-ai/yc-bench
	task_id: medium
	value: 2100000
	source:
	url: https://huggingface.co/MiniMaxAI/MiniMax-M3
	name: MiniMax-M3 model card
	notes: "Model card reports 2.1M (monetary value, final assets fund). The benchmark's 'medium' task is used as the overall evaluation. Metric is monetary, not percentage-based."