Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets
  • 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
dalatexcoder 's Collections
Research Models
Quantized, Ready to use (MLX)
Abliterated, Quantized Production Grade Models
Abliterated, Production Grade Models

Quantized, Ready to use (MLX)

updated 22 days ago

Quantized (using optiq's mixed bit calibration mostly). Base models are not always created by me.

Upvote
-

  • dalatexcoder/MiniCPM5-2B-ARA-MLX-4Bit-optiq-mixed

    Text Generation • 3B • Updated 22 days ago • 99

  • dalatexcoder/MiniCPM5-2B-Heretic-ARA-MLX-4Bit

    Text Generation • 3B • Updated 27 days ago • 89

  • dalatexcoder/Qwen3.8-2B-MLX-4.83B

    Text Generation • 2B • Updated 29 days ago • 364 • 1

  • dalatexcoder/MiniCPM5-2B-5BitL-MLX

    Text Generation • 3B • Updated 29 days ago • 328

  • dalatexcoder/MiniCPM5-1B-Heretic-MLX-4bit

    Text Generation • 1B • Updated about 1 month ago • 48

  • dalatexcoder/Mux-LFM2.5-2.6B-Absolute-Heresy-MLX-5Bit

    Text Generation • 3B • Updated Oct 3 • 150

  • dalatexcoder/Qwen3.8-2B-MLX-4.00B

    Text Generation • 2B • Updated Aug 29 • 18

  • dalatexcoder/Qwen3.8-2B-Heretic-MLX-4.83bit-Mixed

    Text Generation • 2B • Updated Aug 29 • 171 • 2
Upvote
-
  • Collection guide
  • Browse collections
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs