Search public pages, research tools, and SAVRN solutions.
Open-weight model · Image classification
by PyTorch Image Models timm/resnet18.a1_in1k
resnet18.a1_in1k is an open-weight model for image classification from PyTorch Image Models, released under Apache License 2.0. It has 12M parameters. At 16-bit it needs about 0 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index. It draws 2.1M downloads a month.
A ResNet-B image classification model. single layer 7x7 convolution with pooling 1x1 convolution shortcut downsample Trained on ImageNet-1k in timm using recipe template described below.
What it takes to serve resnet18.a1_in1k (12M parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.
| Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits |
|---|---|---|---|---|---|
| 16-bit | 0.0 GB | 0.0 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 0.0 GB | 0.0 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 0.0 GB | 0.0 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Oct 13, 2026.
resnet18.a1_in1k on every accelerator the SAVRN Index prices, at every precision
12M parameters, 93.6 MB of weights, and memory lines that round to 0.0 GB at every precision — resnet18.a1_in1k is a CPU model that the Runs On table lists against a 192 GB MI300X at $1.85 an hour only for completeness. It draws 2M downloads a month as an ImageNet-1k reference checkpoint, and the page ties it to arXiv:1512.03385 and arXiv:2110.00476.
Apache 2.0 permits commercial use with notices kept. Treat it as a baseline rather than a recommendation: it deploys anywhere and trains cheaply, but newer timm recipes at similar latency beat the 2015 architecture on accuracy. Use it to sanity-check data pipelines and as the small end of an accuracy-versus-cost bracket against larger classifiers in this directory; step up within timm when accuracy starts to pay.
By PyTorch Image Models, published under apache-2.0, revision 491b427b45c9.
A ResNet-B image classification model.
This model features: * ReLU activations * single layer 7x7 convolution with pooling * 1x1 convolution shortcut downsample
Trained on ImageNet-1k in timm using recipe template described below.
Recipe details:
* ResNet Strikes Back A1 recipe
* LAMB optimizer with BCE loss
* Cosine LR schedule with warmup
5 files, 93.7 MB in total. The weights are 2 files totalling 93.6 MB in bin, safetensors.
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 46.8 MB | 80c49dee3da4 |
| pytorch_model.bin | Weights | 46.8 MB | 1d92fca7bc19 |
| config.json | Configuration | 755 B | — |
| README.md | Documentation | 38.4 KB | — |
| .gitattributes | Repository | 1.5 KB | — |
Released by PyTorch Image Models through its official repository on Hugging Face. Read the license.
| Precision | Weights in memory |
|---|---|
| As published | 93.6 MB |
| 16-bit | 0.0 GB |
| 8-bit | 0.0 GB |
| 4-bit | 0.0 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
About 0 GB at 16-bit and 0 GB at 4-bit: the weights (12M parameters) plus a working margin. A long context needs more.
At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.
Yes. resnet18.a1_in1k is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.
A ResNet-B image classification model. single layer 7x7 convolution with pooling 1x1 convolution shortcut downsample Trained on ImageNet-1k in timm using recipe template described below. ResNet Strikes Back A3 recipe - Deep Residual Learning for Image Recognition: https://arxiv.org/abs/1512.03385 Explore the dataset and runtime metrics of this model in timm model results.
This model is a fine-tuned ResNet-18 trained to classify fetal ultrasound standard planes. This model was trained on dataset Marc-HealthAI/fetal-planes-classification-dataset-main. No explicit description provided in dataset metadata. Burgos-Artizzu, X.P., Coronado-Gutiérrez, D., Valenzuela-Alcaraz, B. et al. Evaluation of deep convolutional neural networks for automatic classification of common maternal fetal ultrasound planes. Sci Rep 10, 10200 (2020). https://doi.org/10.1038/s41598-020-67076-5 A large dataset of routinely acquired maternal-fetal screening ultrasound images collected from two different hospitals by several operators and ultrasound machines. All images were manually…
This is the model card of a transformers model that has been pushed on the Hub. Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Use the code below to get started with the model. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
A EfficientNet image classification model. Trained on ImageNet-1k in timm using recipe template described below. RandAugment RA2 recipe. Inspired by and evolved from EfficientNet RandAugment recipes. Published as B recipe in ResNet Strikes Back. RMSProp (TF 1.0 behaviour) optimizer, EMA weight averaging Step (exponential decay w/ staircase) LR schedule with warmup Explore the dataset and runtime metrics of this model in timm model results.
A CSPNeXt image classification model. Pretrained on ImageNet-1k by OpenMMLab (RTMDet) and converted to timm format. Name disambiguation: This is the CSPNeXt backbone of RTMDet (OpenMMLab), as implemented in MMDetection. A separate paper, CSPNeXt: A new efficient token hybrid backbone (Chen et al., EAAI 2024, doi:10.1016/j.engappai.2024.107886), uses the same name for a different architecture. These weights do not implement that paper; please cite RTMDet (below) for this model. - https://github.com/open-mmlab/mmdetection/tree/main/configs/rtmdet/classification - https://download.openmmlab.com/mmdetection/v3.0/rtmdet/cspnextrsbpretrain/cspnext-m8xb256-rsb-a1-600ein1k-ecb3bbd9.pth ImageNet-1k…
A RepVGG image classification model. Trained on ImageNet-1k by paper authors. This model architecture is implemented using timm's flexible BYOBNet (Bring-Your-Own-Blocks Network). block / stage layout stem layout output stride (dilation) activation and norm layers channel and spatial / self-attention layers...and also includes timm features common to many other architectures, including: stochastic depth gradient checkpointing layer-wise LR decay per-stage feature extraction Explore the dataset and runtime metrics of this model in timm model results.