Instructions to use MiniMaxAI/MiniMax-M1-40k-hf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MiniMaxAI/MiniMax-M1-40k-hf with Transformers:

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

pipe = pipeline("text-generation", model="MiniMaxAI/MiniMax-M1-40k-hf")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MiniMaxAI/MiniMax-M1-40k-hf")
model = AutoModelForCausalLM.from_pretrained("MiniMaxAI/MiniMax-M1-40k-hf")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use MiniMaxAI/MiniMax-M1-40k-hf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MiniMaxAI/MiniMax-M1-40k-hf"
# 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-M1-40k-hf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/MiniMaxAI/MiniMax-M1-40k-hf

SGLang

How to use MiniMaxAI/MiniMax-M1-40k-hf 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-M1-40k-hf" \
    --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-M1-40k-hf",
		"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-M1-40k-hf" \
        --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-M1-40k-hf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use MiniMaxAI/MiniMax-M1-40k-hf with Docker Model Runner:
```
docker model run hf.co/MiniMaxAI/MiniMax-M1-40k-hf
```

Incompatible model.safetensors.index.json

by MoWi - opened Jul 10, 2025

Discussion

MoWi

Jul 10, 2025

Hi,
First of all, thank you for making hf weights public! I just tried to download the model, but noticed that model.safetensors.index.json contains references to model-00XXX-of-00414.safetensors while the files in the repo are named model-00XXX-of-00413.safetensors, which makes the download/loading of the model fail. Similarly, the file 00413 is referenced in the json, but does not exist in the repo.

I guess that something with computing tensor locations for the model.safetensors.index.json went wrong. Is there any chance to correct this? Thanks!

QscQ

MiniMax org Jul 11, 2025

I will check the problem. You can download the model from https://huggingface.co/MiniMaxAI/MiniMax-M1-40k first, it should be the same.

QscQ

MiniMax org Jul 11, 2025

Thank you so much for your feedback! We’ve identified the issue and have already fixed it. Please try again, and feel free to let us know if you encounter any further problems.

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