An EdgeNeXt image classification model. Trained on ImageNet-1k by paper authors using distillation (USI as per Solving ImageNet).
Open-weight model · Image classification
efficientnet_b0.ra_in1k
by PyTorch Image Models timm/efficientnet_b0.ra_in1k
efficientnet_b0.ra_in1k is an open-weight model for image classification from PyTorch Image Models, released under Apache License 2.0. It has 5M 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 988.6k downloads a month.
A EfficientNet image classification model. Trained on ImageNet-1k in timm using recipe template described below. RandAugment RA recipe. Inspired by and evolved from EfficientNet RandAugment recipes. Published as B recipe in ResNet Strikes Back.
Parameters5M
Context—
Weights42.8 MB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads988.6k
Runs On
What it takes to serve efficientnet_b0.ra_in1k (5M 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.
efficientnet_b0.ra_in1k on every accelerator the SAVRN Index prices, at every precision
SAVRN's Notes on efficientnet_b0.ra_in1k
5M parameters, 42.8 MB of weights, 0.0 GB at every precision: EfficientNet-B0 is edge hardware's oldest bargain, still drawing 704.1k downloads a month, and nothing about serving it involves a data center GPU. The $1.85 MI300X line on our table is a technicality — this runs on a phone SoC or a small dev board, and quantization is almost pointless at 21.4 MB per file.
Apache 2.0 permits commercial embedding with notices kept. The 'ra' is a RandAugment training recipe, published as the B recipe in the ResNet Strikes Back line of work, and the weights come as two 21.4 MB files (safetensors and pytorch) — take one. Released December 2022 with no evaluations on file, it is old but not obsolete: a fine backbone for transfer learning on small custom sets, though newer timm entries at similar size may edge it on accuracy per FLOP.
Model Card
By PyTorch Image Models, published under apache-2.0, revision 1b5383e5f79c.
Model card for efficientnet_b0.ra_in1k
A EfficientNet image classification model. Trained on ImageNet-1k in timm using recipe template described below.
Recipe details:
* RandAugment RA 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
Model Details
- Model Type: Image classification / feature backbone
- Model Stats:
- Params (M): 5.3
- GMACs: 0.4
- Activations (M): 6.7
- Image size: 224 x 224
- Papers:
- EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks: https://arxiv.org/abs/1905.11946
- ResNet strikes back: An improved training procedure in timm: https://arxiv.org/abs/2110.00476
- Dataset: ImageNet-1k
- Original: https://github.com/huggingface/pytorch-image-models
Model Usage
Image Classification
Identity and Version
- Repository
- timm/efficientnet_b0.ra_in1k
- Publisher
- PyTorch Image Models
- Task
- Image classification
- Modality
- Image
- Library
- timm
- Parameters
- 5M parameters
- Languages
- Not stated by the source
- Revision
- 1b5383e5f79cc0f7fc067e372f8f26a5fa73f26a
- First published
- 2022-12-12
- Last updated
- 2025-01-21
Files and Weights
5 files, 42.8 MB in total. The weights are 2 files totalling 42.8 MB in bin, safetensors.
Weights2 files · 42.8 MB
Configuration1 file · 578 B
Documentation1 file · 4.7 KB
Repository1 file · 1.5 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 21.4 MB | d569899762ea |
| pytorch_model.bin | Weights | 21.4 MB | 52487d0cd136 |
| config.json | Configuration | 578 B | — |
| README.md | Documentation | 4.7 KB | — |
| .gitattributes | Repository | 1.5 KB | — |
License and Download
- License
- apache-2.0
- Access
- Open weights, no gate
- Download size
- 42.8 MB
Download from PyTorch Image Models
Released by PyTorch Image Models through its official repository on Hugging Face. Read the license.
Built From
- Described by arXiv:1905.11946
- Described by arXiv:2110.00476
- Trained on (disclosed) imagenet-1k
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 42.8 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.
Compare efficientnet_b0.ra_in1k
Questions About efficientnet_b0.ra_in1k
How much GPU memory does efficientnet_b0.ra_in1k need?
About 0 GB at 16-bit and 0 GB at 4-bit: the weights (5M parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run efficientnet_b0.ra_in1k on?
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.
Can I use efficientnet_b0.ra_in1k commercially?
Yes. efficientnet_b0.ra_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.
Similar Models
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.
A DeiT image classification model. Trained on ImageNet-1k by paper authors. - Training data-efficient image transformers & distillation through attention: https://arxiv.org/abs/2012.12877 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-simagenet600e-ea671761.pth ImageNet-1k validation…
A MobileNet-v3 image classification model. Trained on ImageNet-1k in Tensorflow by paper authors, ported to PyTorch by Ross Wightman. Explore the dataset and runtime metrics of this model in timm model results.
A MobileNet-V4 image classification model. Trained on ImageNet-1k by Ross Wightman. Trained with timm scripts using hyper-parameters inspired by the MobileNet-V4 paper with timm enhancements. NOTE: So far, these are the only known MNV4 weights. Official weights for Tensorflow models are unreleased. - MobileNetV4 -- Universal Models for the Mobile Ecosystem: https://arxiv.org/abs/2404.10518