Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Docs
  • Enterprise
  • Pricing

  • Log In
  • Sign Up
cortecs 's Collections
Sparse FP4 Compression

Sparse FP4 Compression

updated 13 days ago

Suite of Qwen 3 models, compressed using sparsification and 4-bit floating point precision for low-resource deployment.

Upvote
1

  • cortecs/Qwen3-8B-NVFP4

    5B • Updated 13 days ago • 19

  • cortecs/Qwen3-8B-NVFP4A16

    5B • Updated 13 days ago • 9

  • cortecs/Qwen3-8B-clean-sparse-nvfp4a16

    5B • Updated 13 days ago • 9

  • cortecs/Qwen3-8B-clean-sparse-finetuned-0.1-nvfp4a16

    5B • Updated 13 days ago • 9

  • cortecs/Qwen3-8B-clean-sparse

    6B • Updated 13 days ago • 9

  • cortecs/Qwen3-8B-clean-sparse-finetuned-0.01-nvfp4a16

    5B • Updated 13 days ago • 6
Upvote
1
  • Collection guide
  • Browse collections
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs