MiniMax-M2.7-AWQ
Base model: MiniMax/MiniMax-M2.7
This repo quantizes the model using data-free quantization tool.
(no calibration dataset was involved)
【Dependencies / Installation】
vllm>=0.19.0
transformers>=5.5.4
As of 2026-04-16, make sure your system has cuda12.8 or cuda13.0 installed.
Then, create a fresh Python environment (e.g. python3.12 venv) and run:
pip install vllm==0.19.0
pip install transformers==5.5.4
【vLLM Startup Command】
Note: When launching with TP=8, include --enable-expert-parallel;
otherwise the expert tensors wouldn’t be evenly sharded across GPU devices.
export VLLM_SLEEP_WHEN_IDLE=1
export VLLM_USE_DEEP_GEMM=0
export VLLM_USE_FLASHINFER_MOE_FP16=1
export VLLM_USE_FLASHINFER_SAMPLER=0
export OMP_NUM_THREADS=4
vllm serve \
__YOUR_PATH__/tclf90/MiniMax-M2.7-AWQ \
--served-model-name MY_MODEL \
--max-num-seqs 32 \
--max-model-len 32768 \
--gpu-memory-utilization 0.9 \
--tensor-parallel-size 8 \
--enable-expert-parallel \
--enable-auto-tool-choice \
--tool-call-parser minimax_m2 \
--reasoning-parser minimax_m2_append_think \
--trust-remote-code \
--host 0.0.0.0 \
--port 8000
【Logs】
2026-04-20
1. Initial commit
【Model Files】
| File Size | Last Updated |
|---|---|
122GiB | 2026-04-20 |
【Model Download】
from modelscope import snapshot_download
snapshot_download('tclf90/MiniMax-M2.7-AWQ', cache_dir="your_local_path")
【Overview】
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-source 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
- MiniMax M2.7 is also available on NVIDIA NIM Endpoint
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.
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
Contact us at model@minimax.io.