Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets
  • 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

HelloSun
/
qwen38_27bq40

Text Generation
GGUF
llama.cpp
cpu
avx512-vnni
amx
qwen3.5
qwen3.8
Model card Files Files and versions
xet
Community
qwen38_27bq40
736 kB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 8 commits
HelloSun's picture
HelloSun
Add DFlash2 CPU speed benchmarks (n_max 3/5/7)
a57bd00 verified 3 days ago
  • benchmarks
    Add DFlash2 CPU speed benchmarks (n_max 3/5/7) 3 days ago
  • patches
    Q4_0: MTP speculative decoding (draft-mtp, k=3), CPY small-row threading fix, data and model card 3 days ago
  • .gitattributes
    1.52 kB
    initial commit 3 days ago
  • README.md
    14.7 kB
    MTP draft length sweep k=3..6: decode, prefill, acceptance (k=3 best) 3 days ago
  • build.sh
    7.86 kB
    build.sh: add opt-in DFlash2 speculative decoding (DFLASH=1) 3 days ago