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

hipfire-models
/
LFM2.5-8B-A1B

Text Generation
hipfire
amd
rdna
quantized
lfm2.5
liquid
Mixture of Experts
edge
Model card Files Files and versions
xet
Community
LFM2.5-8B-A1B
4.66 GB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 4 commits
schuttdev's picture
schuttdev
registry overhaul: v3-awq-f1 / q8 / mq4-moe
e04f7b1 verified 2 months ago
  • .gitattributes
    1.57 kB
    Add lfm2.5-8b-a1b.mq4 (hipfire MQ4, LiquidAI chat template injected into HFQ metadata; validated coherent on gfx1100) 3 months ago
  • LICENSE
    10.6 kB
    Add model card + LFM Open License v1.0 (verbatim from LiquidAI/LFM2.5-8B-A1B upstream license) 3 months ago
  • README.md
    3.11 kB
    Add model card + LFM Open License v1.0 (verbatim from LiquidAI/LFM2.5-8B-A1B upstream license) 3 months ago
  • lfm2.5-8b-a1b.mq4
    4.66 GB
    xet
    registry overhaul: v3-awq-f1 / q8 / mq4-moe 2 months ago