Search public pages, research tools, and SAVRN solutions.
Open-weight model · Image classification
by PyTorch Image Models timm/repvgg_a0.rvgg_in1k
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).
What it takes to serve repvgg_a0.rvgg_in1k (9M 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 Sep 18, 2026.
What does it cost to keep a 9 million parameter image classifier running in your own rack? Close to nothing beyond the accelerator you already own. Weights and working memory both round to 0.0 GB at 16-bit, 8-bit and 4-bit, the five files total about 73 MB, and the cheapest Index listing is a single MI300X at $1.85 per hour on-demand. The sensible deployment is as a resident model on shared hardware or as a feature extractor, since timm exposes per-stage feature extraction.
The license is MIT: commercial use, modification and redistribution are permitted provided the copyright and permission notices stay attached. It was trained on ImageNet-1k, described in arXiv:2101.03697, so any other label set means a fine-tune. And the timm release dates from August 23, 2023 with a last update on January 21, 2025, so confirm you are loading the current weights.
By PyTorch Image Models, published under mit, revision e292d220aa8b.
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).
BYOBNet allows configuration of: * 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
5 files, 73.2 MB in total. The weights are 2 files totalling 73.2 MB in bin, safetensors.
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 36.6 MB | 2b2bfd7feff2 |
| pytorch_model.bin | Weights | 36.7 MB | d8d1275b0e8a |
| config.json | Configuration | 645 B | — |
| README.md | Documentation | 4.5 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 | 73.2 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 (9M 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. repvgg_a0.rvgg_in1k is released under MIT License. The MIT License is a short permissive license. It permits commercial use, modification and redistribution, provided the copyright notice and permission notice are included.
A ConvNeXt-V2 image classification model. Pretrained with a fully convolutional masked autoencoder framework (FCMAE) and fine-tuned on ImageNet-1k. Explore the dataset and runtime metrics of this model in timm model results. All timing numbers from eager model PyTorch 1.13 on RTX 3090 w/ AMP.
A DenseNet image classification model. Pretrained on ImageNet-1k in timm by Ross Wightman using RandAugment RA recipe. Related to B recipe in ResNet Strikes Back.
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 A1 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.
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.
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 Vision Transformer (ViT) image classification model. Trained on ImageNet-21k and fine-tuned on ImageNet-1k (with additional augmentation and regularization) in JAX by paper authors, ported to PyTorch by Ross Wightman. - How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers: https://arxiv.org/abs/2106.10270 - An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale: https://arxiv.org/abs/2010.11929v2 Explore the dataset and runtime metrics of this model in timm model results.