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
YoozLabs 's Collections
Yooz Models
Yooz Working Models
Lean QAT MLX

Lean QAT MLX

updated 17 days ago

QAT quality at honest 4-bit size for Apple Silicon: uniform 4-bit g64 MLX builds, no silent 8-bit upgrades. Yooz Labs (yooz.live).

Upvote
-

  • YoozLabs/gemma-4-E4B-it-qat-lean-4bit-mlx

    Text Generation • 1B • Updated 18 days ago • 192

  • YoozLabs/gemma-4-12B-it-qat-lean-4bit-mlx

    Text Generation • 12B • Updated 18 days ago • 269

  • YoozLabs/Qwen3.5-0.8B-qat-lean-4bit-mlx

    Text Generation • 0.1B • Updated 9 days ago • 129

  • YoozLabs/Qwen3.5-4B-qat-lean-4bit-mlx

    Text Generation • 0.7B • Updated 9 days ago • 171
Upvote
-
  • Collection guide
  • Browse collections
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs