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
      • Hardware
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

cfontes
/
qwen3.8-27b-mlx-dflash2

MLX
speculative-decoding
qwen
apple-silicon
dflash2
Model card Files Files and versions
xet
Community
2

Instructions to use cfontes/qwen3.8-27b-mlx-dflash2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • MLX

    How to use cfontes/qwen3.8-27b-mlx-dflash2 with MLX:

    # Download the model from the Hub
    pip install huggingface_hub[hf_xet]
    
    huggingface-cli download --local-dir qwen3.8-27b-mlx-dflash2 cfontes/qwen3.8-27b-mlx-dflash2
  • Notebooks
  • Google Colab
  • Kaggle
  • Local Apps Settings
  • LM Studio
  • Atomic Chat
New discussion
Resources
  • PR & discussions documentation
  • Code of Conduct
  • Hub documentation

M5 Max results — DFlash2 transfers to differently-quantized targets, 1.5–1.9x measured (corrected)

2
#2 opened 11 days ago by
KaedeTai
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs