Instructions to use bullerwins/MiniMax-M2.7-REAP-172B-AWQ-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bullerwins/MiniMax-M2.7-REAP-172B-AWQ-4bit with Transformers:

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

pipe = pipeline("text-generation", model="bullerwins/MiniMax-M2.7-REAP-172B-AWQ-4bit", 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("bullerwins/MiniMax-M2.7-REAP-172B-AWQ-4bit", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("bullerwins/MiniMax-M2.7-REAP-172B-AWQ-4bit", 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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use bullerwins/MiniMax-M2.7-REAP-172B-AWQ-4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bullerwins/MiniMax-M2.7-REAP-172B-AWQ-4bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bullerwins/MiniMax-M2.7-REAP-172B-AWQ-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/bullerwins/MiniMax-M2.7-REAP-172B-AWQ-4bit

SGLang

How to use bullerwins/MiniMax-M2.7-REAP-172B-AWQ-4bit 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 "bullerwins/MiniMax-M2.7-REAP-172B-AWQ-4bit" \
    --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": "bullerwins/MiniMax-M2.7-REAP-172B-AWQ-4bit",
		"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 "bullerwins/MiniMax-M2.7-REAP-172B-AWQ-4bit" \
        --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": "bullerwins/MiniMax-M2.7-REAP-172B-AWQ-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use bullerwins/MiniMax-M2.7-REAP-172B-AWQ-4bit with Docker Model Runner:
```
docker model run hf.co/bullerwins/MiniMax-M2.7-REAP-172B-AWQ-4bit
```

GSM8K-Platinum Snapshot

This AWQ 4-bit export was benchmarked locally with vllm against gsm8k_platinum_cot_llama using the MiniMax-recommended sampling parameters (temperature=1.0, top_p=0.95, top_k=40) and the default system prompt:

You are a helpful assistant. Your name is MiniMax-M2.7 and is built by MiniMax.

vLLM launch command

vllm serve bullerwins/MiniMax-M2.7-REAP-172B-AWQ-4bit \
  --served-model-name MiniMax-M2.7 \
  --max-num-seqs 32 \
  --max-model-len auto \
  --gpu-memory-utilization 0.9 \
  -tp 8 \
  --enable-expert-parallel \
  --enable-auto-tool-choice \
  --tool-call-parser minimax_m2 \
  --reasoning-parser minimax_m2 \
  --trust-remote-code \
  --host 0.0.0.0 \
  --port 5000

Benchmark command

source .venv/bin/activate
lm_eval run \
  --model local-chat-completions \
  --tasks gsm8k_platinum_cot_llama \
  --model_args "model=MiniMax-M2.7,max_length=196608,base_url=http://127.0.0.1:5000/v1/chat/completions,num_concurrent=32,max_retries=3,tokenized_requests=False,tokenizer_backend=None,timeout=2400,eos_string=</s>" \
  --apply_chat_template \
  --fewshot_as_multiturn \
  --system_instruction "You are a helpful assistant. Your name is MiniMax-M2.7 and is built by MiniMax." \
  --gen_kwargs do_sample=True temperature=1.0 top_p=0.95 top_k=40 max_gen_toks=8192 \
  --num_fewshot 8 \
  --seed 42 \
  --output_path benchmark_results/minimax_m27_gsm8k_<runstamp> \
  --log_samples

Local AWQ results

Variant	Backend	Seed(s)	Flexible EM	Strict EM	Notes
MiniMax-M2.7-REAP-172B-AWQ-4bit	Local vLLM	42	0.9711 +- 0.0048	0.9711 +- 0.0048	Full run, 1209 examples
MiniMax-M2.7-REAP-172B-AWQ-4bit	Local vLLM	1234	0.9702 +- 0.0049	0.9694 +- 0.0050	Full run, 1209 examples
MiniMax-M2.7-REAP-172B-AWQ-4bit	Local vLLM	5678	0.9727 +- 0.0047	0.9711 +- 0.0048	Full run, 1209 examples
MiniMax-M2.7-REAP-172B-AWQ-4bit	Local vLLM	mean of 3 runs	0.9713	0.9705	Mean across seeds 42 / 1234 / 5678

Comparison with original model weights via OpenRouter

Variant	Backend	Seed(s)	Flexible EM	Strict EM	Notes
MiniMax-M2.7 original weights	OpenRouter	42	0.9744 +- 0.0045	0.9735 +- 0.0046	9 late null content generations
MiniMax-M2.7 original weights	OpenRouter	1234	0.9702 +- 0.0049	0.9686 +- 0.0050	10 late null content generations; runtime about 1:22:21
MiniMax-M2.7 original weights	OpenRouter	mean of 2 runs	0.9723	0.9711	Mean across seeds 42 / 1234
MiniMax-M2.7-REAP-172B-AWQ-4bit	Local vLLM	mean of 3 runs	0.9713	0.9705	About 0.10 flexible / 0.06 strict points below the two-run OpenRouter mean

OpenRouter reference command:

source .venv/bin/activate
OPENAI_API_KEY="$OPENROUTER_API_KEY" lm-eval run \
  --model local-chat-completions \
  --tasks gsm8k_platinum_cot_llama \
  --model_args "model=minimax/minimax-m2.7,base_url=https://openrouter.ai/api/v1/chat/completions,num_concurrent=2,max_retries=3,tokenized_requests=False,tokenizer_backend=None,timeout=1200,max_length=32768,seed=42" \
  --apply_chat_template \
  --fewshot_as_multiturn \
  --system_instruction "You are a helpful assistant. Your name is MiniMax-M2.7 and is built by MiniMax." \
  --gen_kwargs do_sample=True temperature=1.0 top_p=0.95 top_k=40 max_gen_toks=1024 \
  --num_fewshot 8 \
  --seed 42 \
  --output_path results/openrouter_minimax_m27_gsm8k_platinum_full \
  --log_samples

Join Our 💬 WeChat | 🧩 Discord community.

MiniMax Agent | ⚡️ API | CLI | MiniMax Website

🤗 Hugging Face | 🐙 GitHub | 🤖️ ModelScope | 📄 LICENSE

MiniMax-M2.7 is our first model deeply participating in its own evolution. M2.7 is capable of building complex agent harnesses and completing highly elaborate productivity tasks, leveraging Agent Teams, complex Skills, and dynamic tool search. For more details, see our blog post.

Model Self-Evolution

M2.7 initiates a cycle of model self-evolution: during development, we let the model update its own memory, build dozens of complex skills for RL experiments, and improve its own learning process based on experiment results. An internal version of M2.7 autonomously optimized a programming scaffold over 100+ rounds — analyzing failure trajectories, modifying code, running evaluations, and deciding to keep or revert — achieving a 30% performance improvement. On MLE Bench Lite (22 ML competitions), M2.7 achieved a 66.6% medal rate, second only to Opus-4.6 and GPT-5.4.

Professional Software Engineering

M2.7 delivers outstanding real-world programming capabilities spanning log analysis, bug troubleshooting, refactoring, code security, and machine learning. Beyond code generation, M2.7 demonstrates strong system-level reasoning — correlating monitoring metrics, conducting trace analysis, verifying root causes in databases, and making SRE-level decisions. Using M2.7, we have reduced live production incident recovery time to under three minutes on multiple occasions.

On SWE-Pro, M2.7 achieved 56.22%, matching GPT-5.3-Codex, with even stronger performance on real-world engineering benchmarks: SWE Multilingual (76.5) and Multi SWE Bench (52.7). On VIBE-Pro (55.6%), M2.7 is nearly on par with Opus 4.6. On Terminal Bench 2 (57.0%) and NL2Repo (39.8%), M2.7 demonstrates deep understanding of complex engineering systems. M2.7 also supports native Agent Teams for multi-agent collaboration with stable role identity and autonomous decision-making.

Professional Work

M2.7 achieved an ELO score of 1495 on GDPval-AA (highest among open-weight models), surpassing GPT5.3. It handles Word, Excel, and PPT with high-fidelity multi-round editing, producing editable deliverables. On Toolathon, M2.7 reached 46.3% accuracy (global top tier), and maintains 97% skill compliance across 40+ complex skills on MM Claw. On the MM Claw end-to-end benchmark, M2.7 achieved 62.7%, close to Sonnet 4.6.

Entertainment

M2.7 features strengthened character consistency and emotional intelligence. We open-sourced OpenRoom, an interactive demo that places AI interaction within a Web GUI space with real-time visual feedback and scene interactions. Try it at openroom.ai.

How to Use

MiniMax Agent: https://agent.minimax.io/
MiniMax API: https://platform.minimax.io/
Token Plan: https://platform.minimax.io/subscribe/token-plan

Local Deployment Guide

Download the model from HuggingFace repository: https://huggingface.co/MiniMaxAI/MiniMax-M2.7

We recommend using the following inference frameworks (listed alphabetically) to serve the model:

SGLang

We recommend using SGLang to serve MiniMax-M2.7. Please refer to our SGLang Deployment Guide.

vLLM

We recommend using vLLM to serve MiniMax-M2.7. Please refer to our vLLM Deployment Guide.

Transformers

We recommend using Transformers to serve MiniMax-M2.7. Please refer to our Transformers Deployment Guide.

ModelScope

You also can get model weights from modelscope.

NVIDIA NIM

MiniMax M2.7 is also available on NVIDIA NIM Endpoint.

Inference Parameters

We recommend using the following parameters for best performance: temperature=1.0, top_p = 0.95, top_k = 40. Default system prompt:

You are a helpful assistant. Your name is MiniMax-M2.7 and is built by MiniMax.

Tool Calling Guide

Please refer to our Tool Calling Guide.

Contact Us

Downloads last month: 207

Safetensors

Model size

28B params

Tensor type

I64

I32

BF16

Model tree for bullerwins/MiniMax-M2.7-REAP-172B-AWQ-4bit

Base model

MiniMaxAI/MiniMax-M2.7

Quantized

(108)

this model

Collection including bullerwins/MiniMax-M2.7-REAP-172B-AWQ-4bit

MiniMax-M2.7 REAP

Collection

6 items • Updated Apr 20 • 1