Instructions to use cerebras/MiniMax-M2-REAP-162B-A10B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cerebras/MiniMax-M2-REAP-162B-A10B with Transformers:

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

pipe = pipeline("text-generation", model="cerebras/MiniMax-M2-REAP-162B-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-162B-A10B", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("cerebras/MiniMax-M2-REAP-162B-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-162B-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-162B-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-162B-A10B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/cerebras/MiniMax-M2-REAP-162B-A10B

SGLang

How to use cerebras/MiniMax-M2-REAP-162B-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-162B-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-162B-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-162B-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-162B-A10B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use cerebras/MiniMax-M2-REAP-162B-A10B with Docker Model Runner:
```
docker model run hf.co/cerebras/MiniMax-M2-REAP-162B-A10B
```

Tool Use Benchmarks

by louis-szeto - opened Nov 15, 2025

Discussion

louis-szeto

Nov 15, 2025

•

edited Nov 15, 2025

Hi! Thanks for the great work. Do you also have the benchmark scores for tool use and browser comp? MiniMax M2 is targeted to be the best agent with a smaller size, so it would be helpful if these benchmarks are provided for reference as well.

And also, do you have the recommended sampling parameters?

lazarevich

Cerebras org Nov 17, 2025

@louis-szeto we're working on adding more tool calling / agentic evals for this model, just added tau2-bench telecom and BFCLv3. note that not discarding the think traces (via --reasoning-parser minimax_m2_append_think in vLLM) does boost performance at the expense of larger KV cache. on tau2-bench telecom in particular, it's a boost of a few percentage points, we're going to add that soon.

for sampling, we're following the original MiniMax guide (temperature=1.0, top_p = 0.95, top_k = 40). we tried greedy with tool calling and it's considerably worse.

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