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
```

Low generation speed.

#36

by Yurkoff - opened Nov 7, 2025

Discussion

Yurkoff

Nov 7, 2025

Generation speed for MiniMax-M2 :14 tokens/sec.

minimax-m2 | (APIServer pid=1) INFO 11-07 09:22:55 [loggers.py:221] Engine 000: Avg prompt throughput: 1139.4 tokens/s, Avg generation throughput: 3.8 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 7.6%, Prefix cache hit rate: 16.5%
minimax-m2 | (APIServer pid=1) INFO 11-07 09:23:05 [loggers.py:221] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 14.7 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 7.7%, Prefix cache hit rate: 16.5%
minimax-m2 | (APIServer pid=1) INFO 11-07 09:23:15 [loggers.py:221] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 13.4 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 7.8%, Prefix cache hit rate: 16.5%
minimax-m2 | (APIServer pid=1) INFO 11-07 09:23:25 [loggers.py:221] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 14.1 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 7.9%, Prefix cache hit rate: 16.5%
minimax-m2 | (APIServer pid=1) INFO 11-07 09:23:35 [loggers.py:221] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 13.8 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 8.0%, Prefix cache hit rate: 16.5%
minimax-m2 | (APIServer pid=1) INFO 11-07 09:23:45 [loggers.py:221] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 13.7 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 8.1%, Prefix cache hit rate: 16.5%
minimax-m2 | (APIServer pid=1) INFO 11-07 09:23:55 [loggers.py:221] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 13.9 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 8.2%, Prefix cache hit rate: 16.5%
minimax-m2 | (APIServer pid=1) INFO 11-07 09:24:05 [loggers.py:221] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 13.7 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 8.3%, Prefix cache hit rate: 16.5%
minimax-m2 | (APIServer pid=1) INFO 11-07 09:24:15 [loggers.py:221] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 13.3 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 8.4%, Prefix cache hit rate: 16.5%
minimax-m2 | (APIServer pid=1) INFO 11-07 09:24:25 [loggers.py:221] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 13.5 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 8.4%, Prefix cache hit rate: 16.5%

Generation speed for Qwen3-235B-A22B-Instruct-2507: 24 tokens/sec.

Inference was performed on 4 x H100 GPUs. In both cases, "chat_template_kwargs": {"enable_thinking": False} was used.

Yurkoff

Nov 7, 2025

It seems that adding the parameter "chat_template_kwargs": {"enable_thinking": False} does not disable reasoning. Each model response begins with the <think> tag.
This raises an additional question: how can I disable reasoning during inference?

The parameters I used to run VLLM:

--gpu-memory-utilization 0.90 \
--max-model-len 32768 \
--tensor-parallel-size 4 \
--trust-remote-code \
--enable-auto-tool-choice \
--tool-call-parser minimax_m2 \
--reasoning-parser minimax_m2_append_think

rogeryoungh

MiniMax org Dec 1, 2025

For optimal performance on H100 and H20 GPUs with this MoE model, we recommend using DeepGEMM for linear layers while disabling it for MoE expert layers.

https://docs.vllm.ai/projects/recipes/en/latest/MiniMax/MiniMax-M2.html#deepgemm-usage

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