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

basecompute
/
Qwen3.8-27B

Text Generation
basert
apple-silicon
quantized
Model card Files Files and versions
xet
Community
3
Qwen3.8-27B
46.8 GB
Ctrl+K
Ctrl+K
  • 2 contributors
History: 7 commits
prabodbc's picture
prabodbc
Re-convert with the Qwen MTP head (header.speculator): basertd --speculate mtp-head (#2)
85505e1 about 1 month ago
  • .gitattributes
    1.69 kB
    Upload Qwen3.8-27B-Q4-mtp.base with huggingface_hub 3 months ago
  • Qwen3.8-27B-Q4.base
    17.8 GB
    xet
    Re-convert with the Qwen MTP head (header.speculator): basertd --speculate mtp-head (#2) about 1 month ago
  • Qwen3.8-27B-Q8.base
    28.9 GB
    xet
    Re-convert with the Qwen MTP head (header.speculator): basertd --speculate mtp-head (#2) about 1 month ago
  • README.md
    886 Bytes
    Add model card and config 3 months ago
  • config.json
    51 Bytes
    Add model card and config 3 months ago