Instructions to use MiniMaxAI/MiniMax-M2.5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MiniMaxAI/MiniMax-M2.5 with Transformers:

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

pipe = pipeline("text-generation", model="MiniMaxAI/MiniMax-M2.5", 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-M2.5", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("MiniMaxAI/MiniMax-M2.5", 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-M2.5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MiniMaxAI/MiniMax-M2.5"
# 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-M2.5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/MiniMaxAI/MiniMax-M2.5

SGLang

How to use MiniMaxAI/MiniMax-M2.5 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-M2.5" \
    --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-M2.5",
		"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-M2.5" \
        --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-M2.5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use MiniMaxAI/MiniMax-M2.5 with Docker Model Runner:
```
docker model run hf.co/MiniMaxAI/MiniMax-M2.5
```

MiniMax-M2.5

Commit History

Add YC-Bench benchmark result (avg $230,465)

cedce78
verified

RiddleHe commited on Apr 2

Add evaluation results for GPQA, HLE (#3)

f710177

SaylorTwift HF Staff commited on Mar 10

Add evaluation results on SWE-Bench Verified (#42)

1825d90

nielsr HF Staff commited on Mar 10

Create LICENSE-MODEL

ab0ddff
verified

he commited on Mar 6

Update README.md

1248334
verified

he commited on Feb 16

Update README.md

37649bd
verified

he commited on Feb 14

Update README.md

3040bea
verified

he commited on Feb 13

Update README.md

2663734
verified

he commited on Feb 13

Update README.md

3e16da2

xuebi commited on Feb 13

Upload bench_12.png

c6c3633
verified

rogeryoungh commited on Feb 13

update: tool calling guide

5fb9455

xuebi commited on Feb 13

update configs

134ae7c

xuebi commited on Feb 12

Add files using upload-large-folder tool

9ba43d5
verified

windniw commited on Feb 12

Add files using upload-large-folder tool

afa2694
verified

windniw commited on Feb 12

Add files using upload-large-folder tool

8c436e5
verified

windniw commited on Feb 12

update docs

6ff2856

xuebi commited on Feb 12

Upload 13 files

aa487ef
verified

windniw commited on Feb 12

initial commit

e838ad0
verified

MiniMax-AI commited on Feb 12

Commit History

Add YC-Bench benchmark result (avg $230,465) cedce78 verified

Add evaluation results for GPQA, HLE (#3) f710177

Add evaluation results on SWE-Bench Verified (#42) 1825d90

Create LICENSE-MODEL ab0ddff verified

Update README.md 1248334 verified

Update README.md 37649bd verified

Update README.md 3040bea verified

Update README.md 2663734 verified

Update README.md 3e16da2

Upload bench_12.png c6c3633 verified

update: tool calling guide 5fb9455

update configs 134ae7c

Add files using upload-large-folder tool 9ba43d5 verified

Add files using upload-large-folder tool afa2694 verified

Add files using upload-large-folder tool 8c436e5 verified

update docs 6ff2856

Upload 13 files aa487ef verified

initial commit e838ad0 verified

Add YC-Bench benchmark result (avg $230,465)

cedce78
verified

Add evaluation results for GPQA, HLE (#3)

f710177

Add evaluation results on SWE-Bench Verified (#42)

1825d90

Create LICENSE-MODEL

ab0ddff
verified

Update README.md

1248334
verified

Update README.md

37649bd
verified

Update README.md

3040bea
verified

Update README.md

2663734
verified

Update README.md

3e16da2

Upload bench_12.png

c6c3633
verified

update: tool calling guide

5fb9455

update configs

134ae7c

Add files using upload-large-folder tool

9ba43d5
verified

Add files using upload-large-folder tool

afa2694
verified

Add files using upload-large-folder tool

8c436e5
verified

update docs

6ff2856

Upload 13 files

aa487ef
verified

initial commit

e838ad0
verified