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
Gorilla4X 's Collections
The Rock8 - RDNA4 fp8

The Rock8 - RDNA4 fp8

updated 25 days ago

RDNA4 (gfx1201) native-fp8, Quark-quantized. Source + container: github.com/The-Monk/The-Rock8 🦆 Got any weights?

Upvote
1

  • Gorilla4X/Quacken-8B-FP8

    Text Generation • 8B • Updated 25 days ago • 248

  • Gorilla4X/Quacken-R1-14B-FP8

    Text Generation • 15B • Updated 25 days ago • 224

  • Gorilla4X/Quacken-27B-FP8

    Text Generation • 27B • Updated 25 days ago • 459

  • Gorilla4X/Quacken-35B-A3B-FP8

    Text Generation • 36B • Updated 24 days ago • 669

  • Gorilla4X/Quacken-Ornith-35B-FP8

    Text Generation • 35B • Updated 25 days ago • 186

  • Gorilla4X/Bonsai-8B-Ternary-RDNA4

    8B • Updated 25 days ago • 287

    Note Async spec-decode showcase: ternary Q2 self-draft, +66% byte-identical


  • Gorilla4X/Quacken-27B-NVFP4

    Text Generation • 27B • Updated 25 days ago • 68

    Note Mixed FP4-MLP/FP8-attn: 23GB single-card, PPL 6.88, +30% decode vs fp8

Upvote
1
  • Collection guide
  • Browse collections
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs