microsoft / image-classification Open weights updated 2 years ago

resnet-18

Name: resnet-18
Author: microsoft

ResNet model trained on imagenet-1k. It was introduced in the paper Deep Residual Learning for Image Recognition and first released in this repository.

Params

12 M

Context

—

Downloads 30d

728 K

Likes

Commercial use: allowed apache-2.0 Not gated SAFETENSORS View on Hugging Face ↗

Download history

daily snapshots · 21 days

728 K222 K

Oct 4Oct 11Oct 18Oct 24

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	f32	0.0 GB	0.6 GB	✅ Runs comfortably

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Specifications

Architecture: ResNetForImageClassification
Parameters: 12 M
Tensor type: F32
Licence: apache-2.0
First seen on the Hub: 2022-03-16
Training datasets: imagenet-1k
Added to our catalog: 2026-10-04

Compare with any image-classification model

Popular comparisons

mobilenetv3_small_100.lamb_in1k 17.0 M vit-base-patch16-224 14.0 M Gender-Classifier-Mini 6.1 M resnet18.a1_in1k 2.0 M tf_efficientnetv2_s.in21k_ft_in1k 1.9 M efficientnet_b0.ra_in1k 673 K