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

cfontes
/
qwen-dflash2-spark

Text Generation
vllm
dflash2
speculative-decoding
nvfp4
qwen3
dgx-spark
gb10
Model card Files Files and versions
xet
Community
qwen-dflash2-spark / docs
Ctrl+K
Ctrl+K
  • 1 contributor
History: 2 commits
cfontes's picture
cfontes
Add prefill benchmark (~3.4k tok/s peak) + GH canonical link
67da175 verified 3 days ago
  • README-agent.md
    1.6 kB
    Qwen3.8-27B DFlash2 on 2x DGX Spark: one-stop stack (135 tok/s C1, lm_head BF16 fix) 3 days ago
  • architecture.md
    2.59 kB
    Qwen3.8-27B DFlash2 on 2x DGX Spark: one-stop stack (135 tok/s C1, lm_head BF16 fix) 3 days ago
  • results.md
    2.52 kB
    Add prefill benchmark (~3.4k tok/s peak) + GH canonical link 3 days ago