Instructions to use FenomAI/MiniMax-M3-AWQ-INT4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FenomAI/MiniMax-M3-AWQ-INT4 with Transformers:

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

pipe = pipeline("image-text-to-text", model="FenomAI/MiniMax-M3-AWQ-INT4", 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("FenomAI/MiniMax-M3-AWQ-INT4", trust_remote_code=True)
model = AutoModelForMultimodalLM.from_pretrained("FenomAI/MiniMax-M3-AWQ-INT4", 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 FenomAI/MiniMax-M3-AWQ-INT4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FenomAI/MiniMax-M3-AWQ-INT4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FenomAI/MiniMax-M3-AWQ-INT4",
		"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/FenomAI/MiniMax-M3-AWQ-INT4

SGLang

How to use FenomAI/MiniMax-M3-AWQ-INT4 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 "FenomAI/MiniMax-M3-AWQ-INT4" \
    --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": "FenomAI/MiniMax-M3-AWQ-INT4",
		"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 "FenomAI/MiniMax-M3-AWQ-INT4" \
        --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": "FenomAI/MiniMax-M3-AWQ-INT4",
		"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 FenomAI/MiniMax-M3-AWQ-INT4 with Docker Model Runner:
```
docker model run hf.co/FenomAI/MiniMax-M3-AWQ-INT4
```

Version	26.05.01
Calibration	STEM and Agentic
Languages	`EN` `ZH` `HI` `AR` `RU` `JA` `KO` `NL` `FR` `ES`
Model Size	240.30 GB
Contact	Email

Serving with vLLM

This checkpoint needs a patched vLLM (MiniMax-M3 compressed-tensors support). The patch is Python-only, so it installs on top of upstream's precompiled binaries — no CUDA compilation.

Install

# uv (skip if already installed)
curl -LsSf https://astral.sh/uv/install.sh | sh

# clone the fork + fetch the upstream base commit
git clone https://github.com/toncao/vllm.git
cd vllm
git remote add upstream https://github.com/vllm-project/vllm.git
git fetch upstream a7fdfeef72323eb3db6f0620e4ea200290d0ca5a
git checkout minimax-m3-compressed-tensors

# Python 3.12 env + install with upstream precompiled kernels
uv venv --python 3.12
source .venv/bin/activate
VLLM_USE_PRECOMPILED=1 uv pip install -e . --torch-backend=auto

Serve

vllm serve cyankiwi/MiniMax-M3-AWQ-INT4 --block-size 128

MiniMax-M3 is a native multimodal model with 1M context. It has ~428B parameters and ~23B activated parameters.

Highlights:

Native Multimodality: M3 undergoes mixed-modality training from the very first step, enabling deeper semantic fusion across text, image, and video.
Context Scaling via Sparse Attention: M3 introduces MiniMax Sparse Attention (MSA) to improve long context efficiency. M3 delivers 9× prefill and 15× decode speedups compared to M2 at 1M context, reducing per-token compute to 1/20.
Coding & Cowork Capability: M3 achieves frontier-level performance across long-horizon agentic benchmarks, excelling in both coding and cowork.

MiniMax Sparse Attention (MSA)

M3 is powered by MiniMax Sparse Attention (MSA), a high-performance sparse attention operator designed for million-token contexts. Compared with GQA, MSA dramatically reduces the attention compute and memory footprint while preserving model quality.

GQA vs MSA Efficiency Comparison

📄 Read the technical report: arXiv:2606.13392 · Hugging Face Papers

How to Use

M3 supports two reasoning modes:

thinking — for complex reasoning, agentic tasks, and long-horizon collaboration.
non-thinking — for latency-sensitive scenarios such as chat and code completion.

Local Deployment

Download the model:

hf download MiniMaxAI/MiniMax-M3 --local-dir MiniMax-M3

We recommend the following inference frameworks (listed alphabetically) to serve the model:

Inference Parameters

We recommend the following parameters for best performance: temperature=1.0, top_p=0.95, top_k=40.

Contact Us

Downloads last month: 47

Safetensors

Model size

453B params

Tensor type

BF16

I64

I32

Model tree for FenomAI/MiniMax-M3-AWQ-INT4

Base model

MiniMaxAI/MiniMax-M3

Quantized

(50)

this model

Paper for FenomAI/MiniMax-M3-AWQ-INT4

MiniMax Sparse Attention

Paper • 2606.13392 • Published Jun 11 • 152