Instructions to use MiniMaxAI/MiniMax-M2.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MiniMaxAI/MiniMax-M2.1 with Transformers:

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

pipe = pipeline("text-generation", model="MiniMaxAI/MiniMax-M2.1", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("MiniMaxAI/MiniMax-M2.1", trust_remote_code=True)
model = AutoModelForMultimodalLM.from_pretrained("MiniMaxAI/MiniMax-M2.1", 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 Settings

vLLM

How to use MiniMaxAI/MiniMax-M2.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MiniMaxAI/MiniMax-M2.1"
# 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-M2.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/MiniMaxAI/MiniMax-M2.1

SGLang

How to use MiniMaxAI/MiniMax-M2.1 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-M2.1" \
    --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-M2.1",
		"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-M2.1" \
        --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-M2.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use MiniMaxAI/MiniMax-M2.1 with Docker Model Runner:
```
docker model run hf.co/MiniMaxAI/MiniMax-M2.1
```

AntonV HF Staff commited on Jan 7

Commit

1f5d476

1 Parent(s): 200351b

update docs

Browse files

Files changed (2) hide show

docs/transformers_deploy_guide.md +4 -5
docs/transformers_deploy_guide_cn.md +3 -4

docs/transformers_deploy_guide.md CHANGED Viewed

@@ -17,7 +17,7 @@ The deployment process is illustrated below using MiniMax-M2.1 as an example.
 - Python: 3.9 - 3.12
-- Transformers: 4.57.1
 - GPU:
@@ -32,7 +32,7 @@ It is recommended to use a virtual environment (such as **venv**, **conda**, or
 We recommend installing Transformers in a fresh Python environment:
 ```bash
-uv pip install transformers==4.57.1 torch accelerate --torch-backend=auto
 ```
 Run the following Python script to run the model. Transformers will automatically download and cache the MiniMax-M2.1 model from Hugging Face.
@@ -46,7 +46,6 @@ MODEL_PATH = "MiniMaxAI/MiniMax-M2.1"
 model = AutoModelForCausalLM.from_pretrained(
     MODEL_PATH,
     device_map="auto",
-    trust_remote_code=True,
 )
 tokenizer = AutoTokenizer.from_pretrained(MODEL_PATH)
@@ -58,7 +57,7 @@ messages = [
 model_inputs = tokenizer.apply_chat_template(messages, return_tensors="pt", add_generation_prompt=True).to("cuda")
-generated_ids = model.generate(model_inputs, max_new_tokens=100, generation_config=model.generation_config)
 response = tokenizer.batch_decode(generated_ids)[0]
@@ -77,7 +76,7 @@ export HF_ENDPOINT=https://hf-mirror.com
 ### MiniMax-M2 model is not currently supported
-Please check that trust_remote_code=True.
 ## Getting Support

 - Python: 3.9 - 3.12
+- Transformers: 5.0.0.dev0
 - GPU:
 We recommend installing Transformers in a fresh Python environment:
 ```bash
+uv pip install git+https://github.com/huggingface/transformers torch accelerate
 ```
 Run the following Python script to run the model. Transformers will automatically download and cache the MiniMax-M2.1 model from Hugging Face.
 model = AutoModelForCausalLM.from_pretrained(
     MODEL_PATH,
     device_map="auto",
 )
 tokenizer = AutoTokenizer.from_pretrained(MODEL_PATH)
 model_inputs = tokenizer.apply_chat_template(messages, return_tensors="pt", add_generation_prompt=True).to("cuda")
+generated_ids = model.generate(**model_inputs, max_new_tokens=100, generation_config=model.generation_config)
 response = tokenizer.batch_decode(generated_ids)[0]
 ### MiniMax-M2 model is not currently supported
+Please check that you have installed transformers with a version that supports this model.
 ## Getting Support

docs/transformers_deploy_guide_cn.md CHANGED Viewed

@@ -17,7 +17,7 @@
 - Python：3.9 - 3.12
-- Transformers: 4.57.1
 - GPU：
@@ -32,7 +32,7 @@
 建议在全新的 Python 环境中安装 Transformers:
 ```bash
-uv pip install transformers==4.57.1 torch accelerate --torch-backend=auto
 ```
 运行如下 Python 命令运行模型，Transformers 会自动从 Huggingface 下载并缓存 MiniMax-M2.1 模型。
@@ -46,7 +46,6 @@ MODEL_PATH = "MiniMaxAI/MiniMax-M2.1"
 model = AutoModelForCausalLM.from_pretrained(
     MODEL_PATH,
     device_map="auto",
-    trust_remote_code=True,
 )
 tokenizer = AutoTokenizer.from_pretrained(MODEL_PATH)
@@ -58,7 +57,7 @@ messages = [
 model_inputs = tokenizer.apply_chat_template(messages, return_tensors="pt", add_generation_prompt=True).to("cuda")
-generated_ids = model.generate(model_inputs, max_new_tokens=100, generation_config=model.generation_config)
 response = tokenizer.batch_decode(generated_ids)[0]

 - Python：3.9 - 3.12
+- Transformers: 5.0.0.dev0
 - GPU：
 建议在全新的 Python 环境中安装 Transformers:
 ```bash
+uv pip install git+https://github.com/huggingface/transformers torch accelerate
 ```
 运行如下 Python 命令运行模型，Transformers 会自动从 Huggingface 下载并缓存 MiniMax-M2.1 模型。
 model = AutoModelForCausalLM.from_pretrained(
     MODEL_PATH,
     device_map="auto",
 )
 tokenizer = AutoTokenizer.from_pretrained(MODEL_PATH)
 model_inputs = tokenizer.apply_chat_template(messages, return_tensors="pt", add_generation_prompt=True).to("cuda")
+generated_ids = model.generate(**model_inputs, max_new_tokens=100, generation_config=model.generation_config)
 response = tokenizer.batch_decode(generated_ids)[0]