Instructions to use cerebras/MiniMax-M2-REAP-172B-A10B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cerebras/MiniMax-M2-REAP-172B-A10B with Transformers:

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

pipe = pipeline("text-generation", model="cerebras/MiniMax-M2-REAP-172B-A10B", 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("cerebras/MiniMax-M2-REAP-172B-A10B", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("cerebras/MiniMax-M2-REAP-172B-A10B", trust_remote_code=True, device_map="auto")
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 Settings

vLLM

How to use cerebras/MiniMax-M2-REAP-172B-A10B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cerebras/MiniMax-M2-REAP-172B-A10B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cerebras/MiniMax-M2-REAP-172B-A10B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/cerebras/MiniMax-M2-REAP-172B-A10B

SGLang

How to use cerebras/MiniMax-M2-REAP-172B-A10B 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 "cerebras/MiniMax-M2-REAP-172B-A10B" \
    --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": "cerebras/MiniMax-M2-REAP-172B-A10B",
		"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 "cerebras/MiniMax-M2-REAP-172B-A10B" \
        --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": "cerebras/MiniMax-M2-REAP-172B-A10B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use cerebras/MiniMax-M2-REAP-172B-A10B with Docker Model Runner:
```
docker model run hf.co/cerebras/MiniMax-M2-REAP-172B-A10B
```

Tokenizer is wrong

by ilintar - opened Nov 17, 2025

Discussion

ilintar

Nov 17, 2025

I believe the uploaded tokenizer files are wrong, had to add the original tokenizer files to convert to GGUF.

lazarevich

Cerebras org Nov 17, 2025

tokenizer.json was missing, thanks for flagging this, fixed!

lazarevich changed discussion status to closed Nov 17, 2025

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