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
Shiftedx 's Collections
Ornith 1.5 9B Apple Silicon MLX Vision Quants
Ornith 1.5 35B-A3B Apple Silicon MLX/MTPLX Quants
Qwen3.8 27B AEON Ultimate Uncensored MLX Quants
Muse Glimmer 30B Vision MLX Quants
Qwen3.8 27B Abliterated MLX and MTPLX
Qwen3.8-27B MLX and MTPLX
Qwythos-27B-v1 MLX and MTPLX Builds
Tess-4-27B Abliterated MXFP4 Vision MLX + MTPLX
Ornith 1.0 Apple Silicon MLX and MTPLX Builds
Qwopus3.6 35B A3B Coder Abliterated Vision MLX
Qwopus3.6 MLX Quants

Qwythos-27B-v1 MLX and MTPLX Builds

updated Jul 29

Vision-preserving MXFP4 and MXFP8 MLX conversions of empero-ai/Qwythos-27B-v1, plus the self-contained native-MTP MXFP4 build for MTPLX.

Upvote
-

  • Shiftedx/Qwythos-27B-v1-MXFP4-Vision-MLX

    Image-Text-to-Text • 27B • Updated Jul 29 • 85

    Note Standard vision-preserving MXFP4 MLX build.


  • Shiftedx/Qwythos-27B-v1-MXFP8-Vision-MLX

    Image-Text-to-Text • 27B • Updated Jul 29 • 80

    Note Standard vision-preserving MXFP8 MLX build.


  • Shiftedx/Qwythos-27B-v1-MXFP4-Vision-MTPLX

    Image-Text-to-Text • 27B • Updated Jul 29 • 195

    Note Self-contained MXFP4 build with Qwythos's native BF16 MTP head for MTPLX 2.0.1.

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