Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Docs
  • Enterprise
  • Pricing

  • Log In
  • Sign Up
apple 's Collections
FastVLM
MobileCLIP2
DiffuCoder
AIMv2
Core ML Gallery Models
OpenELM Instruct Models
OpenELM Pretrained Models
MobileCLIP Models + DataCompDR Data
TiC-CLIP
DepthPro Models
Core ML Stable Diffusion
Core ML FastViT
Core ML Depth Anything
DFN Models + Data
AIM
DCLM
Core ML Segment Anything 2

FastVLM

updated Sep 2

Efficient Vision Encoding for Vision Language Models

Upvote
103

  • FastVLM: Efficient Vision Encoding for Vision Language Models

    Paper • 2412.13303 • Published Dec 17, 2024 • 70

  • Running
    394
    394

    FastVLM WebGPU

    🍎

    Real-time video captioning powered by FastVLM


  • apple/FastVLM-0.5B

    Text Generation • 0.8B • Updated Sep 3 • 12.7k • 332

  • apple/FastVLM-1.5B

    Text Generation • 2B • Updated Sep 3 • 4.92k • 68

  • apple/FastVLM-7B

    Text Generation • 8B • Updated Sep 3 • 3.97k • 256

  • apple/FastVLM-0.5B-fp16

    0.6B • Updated Sep 3 • 126 • 12

    Note MLX checkpoint


  • apple/FastVLM-1.5B-int8

    0.5B • Updated Sep 3 • 110 • 15

    Note MLX checkpoint


  • apple/FastVLM-7B-int4

    1B • Updated Sep 3 • 126 • 21

    Note MLX checkpoint

Upvote
103
  • Collection guide
  • Browse collections
Company
TOS Privacy About Jobs
Website
Models Datasets Spaces Pricing Docs