Instructions to use MiniMaxAI/MiniMax-M3-MXFP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MiniMaxAI/MiniMax-M3-MXFP8 with Transformers:

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

pipe = pipeline("image-text-to-text", model="MiniMaxAI/MiniMax-M3-MXFP8", 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("MiniMaxAI/MiniMax-M3-MXFP8", trust_remote_code=True)
model = AutoModelForMultimodalLM.from_pretrained("MiniMaxAI/MiniMax-M3-MXFP8", 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 MiniMaxAI/MiniMax-M3-MXFP8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MiniMaxAI/MiniMax-M3-MXFP8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MiniMaxAI/MiniMax-M3-MXFP8",
		"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/MiniMaxAI/MiniMax-M3-MXFP8

SGLang

How to use MiniMaxAI/MiniMax-M3-MXFP8 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 "MiniMaxAI/MiniMax-M3-MXFP8" \
    --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": "MiniMaxAI/MiniMax-M3-MXFP8",
		"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 "MiniMaxAI/MiniMax-M3-MXFP8" \
        --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": "MiniMaxAI/MiniMax-M3-MXFP8",
		"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 MiniMaxAI/MiniMax-M3-MXFP8 with Docker Model Runner:
```
docker model run hf.co/MiniMaxAI/MiniMax-M3-MXFP8
```

MiniMax-M3-MXFP8 / tokenizer_config.json

xuebi

initial commit

2a60e16 about 21 hours ago

raw

history blame contribute delete

11.3 kB

	{
	"add_prefix_space": false,
	"added_tokens_decoder": {
	"200000": {
	"content": "]!p~[",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"200001": {
	"content": "<fim_prefix>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"200002": {
	"content": "<fim_middle>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"200003": {
	"content": "<fim_suffix>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"200004": {
	"content": "<fim_pad>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"200005": {
	"content": "<reponame>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"200006": {
	"content": "<filename>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"200007": {
	"content": "<gh_stars>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"200008": {
	"content": "<issue_start>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"200009": {
	"content": "<issue_comment>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"200010": {
	"content": "<issue_closed>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"200011": {
	"content": "<jupyter_start>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"200012": {
	"content": "<jupyter_text>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"200013": {
	"content": "<jupyter_code>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"200014": {
	"content": "<jupyter_output>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"200015": {
	"content": "<empty_output>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"200016": {
	"content": "<commit_before>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"200017": {
	"content": "<commit_msg>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"200018": {
	"content": "<commit_after>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"200019": {
	"content": "]~b]",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"200020": {
	"content": "[e~[",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"200021": {
	"content": "]!d~[",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"200022": {
	"content": "<function_call>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"200023": {
	"content": "<code_interpreter>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"200024": {
	"content": "]<]speech[>[",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"200025": {
	"content": "]<]image[>[",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"200026": {
	"content": "]<]video[>[",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"200027": {
	"content": "]<]start of speech[>[",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"200028": {
	"content": "]<]end of speech[>[",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"200029": {
	"content": "]<]start of image[>[",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"200030": {
	"content": "]<]end of image[>[",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"200031": {
	"content": "]<]start of video[>[",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"200032": {
	"content": "]<]end of video[>[",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"200033": {
	"content": "]<]vision pad[>[",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"200034": {
	"content": "]~!b[",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"200035": {
	"content": "<jupyter_error>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"200036": {
	"content": "<add_file>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"200037": {
	"content": "<delete_file>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"200038": {
	"content": "<rename_file>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"200039": {
	"content": "<edit_file>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"200040": {
	"content": "<commit_message>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"200041": {
	"content": "<empty_source_file>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"200042": {
	"content": "<repo_struct>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"200043": {
	"content": "<code_context>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"200044": {
	"content": "<file_content>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"200045": {
	"content": "<source_files>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"200046": {
	"content": "<pr_start>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"200047": {
	"content": "<review_comment>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"200048": {
	"content": "<filepath>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"200049": {
	"content": "<file_sep>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"200050": {
	"content": "<think>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"200051": {
	"content": "</think>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"200052": {
	"content": "<tool_call>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"200053": {
	"content": "</tool_call>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"200054": {
	"content": "]<]frame[>[",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"200055": {
	"content": "]<]start of frame[>[",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"200056": {
	"content": "]<]end of frame[>[",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"200057": {
	"content": "<\|content_altered_placeholder\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"200058": {
	"content": "]<]minimax[>[",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"200059": {
	"content": "<mm:think>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"200060": {
	"content": "</mm:think>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": false
	}
	},
	"bos_token": "]~b]",
	"clean_up_tokenization_spaces": false,
	"eos_token": "[e~[",
	"pad_token": "]!p~[",
	"model_max_length": 40960000,
	"tokenizer_class": "PreTrainedTokenizerFast",
	"unk_token": "[e~["
	}