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
d0zz0d 's Collections
Smol MoEs
Sub-5b Things
Sub-2b Things
Sub-5b Parameter T2T LLMs
Sub-5b Parameter IT2T LLMs
Sub-5b T2T LLMs - Finetunes
Sub-2b Parameter T2T LLMs
Sub-2b Parameter IT2T VLMs
Sub-2b T2T LLMs - Finetunes
Sub-1b Parameter T2T LLMs
Sub-1b Parameter IT2T VLMs
>500M LLMs VLMs

Sub-1b Parameter T2T LLMs

updated Sep 3

Lists some sub-1b parameter text-to-text small language models, perfect for edge use, smartphones, or generally weak hardware for below 2GB of RAM.

Upvote
-

  • LiquidAI/LFM2.5-230M

    Text Generation • 0.2B • Updated Aug 19 • 81.9k • 311

  • ibm-granite/granite-4.0-h-350m

    Text Generation • 0.3B • Updated Oct 23, 2025 • 4.13k • 112

  • LiquidAI/LFM2.5-350M

    Text Generation • 0.4B • Updated Aug 5 • 53.4k • 437

    Note the best sub-half-billion parameter model out there


  • ibm-granite/granite-4.0-350m

    Text Generation • 0.4B • Updated Oct 23, 2025 • 23.3k • 71

  • openbmb/BitCPM-CANN-0.5B

    Text Generation • Updated May 23 • 2.77k • 10

  • IFM/K2-Horizon-0.9B

    Text Generation • 1B • Updated 12 days ago • 24.5k • • 97
Upvote
-
  • Collection guide
  • Browse collections
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs