Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

osmapi
/
MiniMax-M2-THRIFT-55-MLX-4bit

MLX
Safetensors
minimax
Mixture of Experts
bfloat16
sglang
custom_code
4-bit precision
Model card Files Files and versions
xet
Community
1

Instructions to use osmapi/MiniMax-M2-THRIFT-55-MLX-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • MLX

    How to use osmapi/MiniMax-M2-THRIFT-55-MLX-4bit with MLX:

    # Download the model from the Hub
    pip install huggingface_hub[hf_xet]
    
    huggingface-cli download --local-dir MiniMax-M2-THRIFT-55-MLX-4bit osmapi/MiniMax-M2-THRIFT-55-MLX-4bit
  • Notebooks
  • Google Colab
  • Kaggle
  • Local Apps
  • LM Studio
New discussion
Resources
  • PR & discussions documentation
  • Code of Conduct
  • Hub documentation

Could you please quantize a 6-bit or 6.5-bit model that requires 93-97GB of memory? Such a model could be deployed on a Mac with 128GB of RAM. Thank you very much!

#1 opened 6 months ago by
mimeng1990
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs