Instructions to use MiniMaxAI/MiniMax-M2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MiniMaxAI/MiniMax-M2 with Transformers:

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

pipe = pipeline("text-generation", model="MiniMaxAI/MiniMax-M2", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MiniMaxAI/MiniMax-M2", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("MiniMaxAI/MiniMax-M2", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
HuggingChat
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use MiniMaxAI/MiniMax-M2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MiniMaxAI/MiniMax-M2"
# 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-M2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/MiniMaxAI/MiniMax-M2

SGLang

How to use MiniMaxAI/MiniMax-M2 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-M2" \
    --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-M2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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-M2" \
        --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-M2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use MiniMaxAI/MiniMax-M2 with Docker Model Runner:
```
docker model run hf.co/MiniMaxAI/MiniMax-M2
```

Can it run on NVIDIA A100 80G * 8 ？

#30

by jetto98 - opened Nov 3, 2025

Discussion

jetto98

Nov 3, 2025

I try to run with sglang ，but it says 'not support fp8e4nv'

krustik

Nov 3, 2025

•

edited Nov 3, 2025

Why?
I can run in latest llama.cpp on ONLY CPU server motherboard with 768Gb RAM total (by 64Gb, i can't find 128Gb RAM too rare). Memory is everything, speed is NOTHING esp with textual models. Server motherboards have CXL tech and 24 RAM slots for a reason! It looks like that https://www.gigabyte.com/Enterprise/Server-Motherboard
I've already run F16 quality which require 465Gb RAM/VRAM and i have a mixed results, the main problem of this model is too much thinking, but it show worse results than GLM4.5 - sometimes code perfect, sometimes broken. In Q8 quality (254Gb RAM) its much worse than GLM4.5.
P.S. my server motherboard is from year 2014, total PC cost with all RAM is kinda $1000. GPUs are usable in video, not in this.

lly0571

Nov 7, 2025

VLLM should support FP8 W8A16

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment