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
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up
ggml-org 's Collections
NVIDIA-Nemotron-3-Nano-Omni
OCR models
Gemma 4
NVIDIA Nemotron 3 Super
Devstral 2
NVIDIA Nemotron 3
Multimodal GGUFs
GLM-V
Ministral 3
EmbeddingGemma 300M
Gemma 3-270m
GPT OSS
Kimi-VL
Gemma 3n
VAD
InternVL 3 and InternVL 2.5
Qwen 2 VL and Qwen 2.5 VL
Qwen 3
SmolVLM GGUF
Gemma 3
llama.cpp presets
GGUF LoRA adapters
llama.vim
Gemma 1.1 GGUFs

OCR models

updated Apr 10
Upvote
11

  • ggml-org/GLM-OCR-GGUF

    0.9B • Updated Mar 10 • 26.4k • 62

  • ggml-org/DeepSeek-OCR-GGUF

    3B • Updated Mar 25 • 13.4k • 9

  • ggml-org/dots.ocr-GGUF

    2B • Updated Apr 5 • 1.09k • 4

  • ggml-org/Qianfan-OCR-GGUF

    4B • Updated Apr 10 • 670 • 3

  • ggml-org/LightOnOCR-1B-1025-GGUF

    0.8B • Updated Oct 24, 2025 • 304 • 14

  • ggml-org/LightOnOCR-2-1B-GGUF

    0.6B • Updated Apr 10 • 335 • 2

    Note Below are generic-purpose small models that can perform OCR task


  • ggml-org/gemma-4-E2B-it-GGUF

    5B • Updated Apr 12 • 75.6k • 70

  • ggml-org/gemma-4-E4B-it-GGUF

    8B • Updated Apr 12 • 112k • 55

  • LiquidAI/LFM2.5-VL-450M-GGUF

    Image-Text-to-Text • 0.4B • Updated Apr 6 • 9.04k • 45

  • unsloth/Qwen3-VL-2B-Instruct-GGUF

    Image-Text-to-Text • 2B • Updated Oct 31, 2025 • 81.8k • 31
Upvote
11
  • Collection guide
  • Browse collections
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs