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
pipenetwork 's Collections
Nemotron TwoTower · MLX
Qwen3.6-35B-A3B — MLX
Ornith-1.0-397B — MLX
GLM-5.2 REAP (expert-pruned)
GLM-5.2 MLX
VISTA MLX
Rio-3.1-Open-30B MLX
Macaron-V1-Preview-749B MLX
Gemma-4-26B-A4B-it MLX
Gemma-4-31B-it MLX
Kimi-K2.7-Code MLX
MiniMax-M3 MLX
Holo-3.1 MLX (computer-use)
Frog (SWE/debugging) MLX
Nemotron-3 MLX (Apple Silicon)

GLM-5.2 REAP (expert-pruned)

updated 16 days ago

REAP expert-pruned GLM-5.2 (smaller/faster). REAP-25 near-lossless (+2.3% PPL); REAP-37 +7.3%; REAP-50 smallest but +37.5%.

Upvote
-

  • pipenetwork/GLM-5.2-REAP25-MLX-4bit

    Text Generation • 562B • Updated 16 days ago • 3.81k • 2

    Note near-lossless (+2.3% PPL)


  • pipenetwork/GLM-5.2-REAP37-MLX-4bit

    Text Generation • 472B • Updated 16 days ago • 2.71k

    Note modest quality cost (+7.3% PPL)


  • pipenetwork/GLM-5.2-REAP50-MLX-4bit

    Text Generation • 381B • Updated 16 days ago • 3.23k • 1

    Note SMALLEST but notably degraded (+37.5% PPL)

Upvote
-
  • Collection guide
  • Browse collections
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs