Instructions to use z-lab/MiniMax-M2.7-DFlash with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use z-lab/MiniMax-M2.7-DFlash with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="z-lab/MiniMax-M2.7-DFlash")# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("z-lab/MiniMax-M2.7-DFlash") model = AutoModel.from_pretrained("z-lab/MiniMax-M2.7-DFlash") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use z-lab/MiniMax-M2.7-DFlash with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "z-lab/MiniMax-M2.7-DFlash" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "z-lab/MiniMax-M2.7-DFlash", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/z-lab/MiniMax-M2.7-DFlash
- SGLang
How to use z-lab/MiniMax-M2.7-DFlash 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 "z-lab/MiniMax-M2.7-DFlash" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "z-lab/MiniMax-M2.7-DFlash", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'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 "z-lab/MiniMax-M2.7-DFlash" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "z-lab/MiniMax-M2.7-DFlash", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use z-lab/MiniMax-M2.7-DFlash with Docker Model Runner:
docker model run hf.co/z-lab/MiniMax-M2.7-DFlash
approvals
are approvals case by case, or whats the approval process like? would love to try it even if its not ready!
wondering that myself! :)
half life 3 is coming
Does this work with M2.7-REAP-172BA10B-NVFP4 versions?
Would love to have access even if it’s not finalized so I can start integrating it with DGX Spark deployments
With Gemma 4 31B they approved access requests only after the model file was updated to the final version.
Maybe they just don't want the incomplete model to start spreading. Reasonable if so.
With Gemma 4 31B they approved access requests only after the model file was updated to the final version.
Maybe they just don't want the incomplete model to start spreading. Reasonable if so.
You see downloads, right ? :D
I pledge to only speak on the results of the final version
access now? :)
damn minimax 3 gonna come before access :(
GTA6 let's gooo
Even if it is a preview release, I'd be happy to at least test and give feedback. :-)
minimax 3 is actually coming soon now, shame this training is gonna be a waste soon
