# edgenext_small.usi_in1k by PyTorch Image Models: Open Model
Source: https://savrn.com/models/edgenext-small-usi-in1k
Markdown alternate of the page above; the site index is https://savrn.com/llms.txt

---

## Runs On

What it takes to serve edgenext_small.usi_in1k (6M 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](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 |
| 8-bit | 0.0 GB | 0.0 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 |
| 4-bit | 0.0 GB | 0.0 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/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](https://savrn.com/ai-index/pricing/gpus), read Oct 23, 2026.

[edgenext_small.usi_in1k on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/edgenext-small-usi-in1k/gpus)

## SAVRN's Notes on edgenext_small.usi_in1k

EdgeNeXt is built for phones and edge devices, and this small version has about 6M parameters. It mixes convolutions with attention to get more accuracy per unit of compute, and the authors trained it on ImageNet-1K using distillation.

The MIT license allows commercial use. If you need an image classifier that runs on-device or on a CPU at high throughput, this is a sensible starting backbone to fine-tune. Measure latency on your actual target hardware, since edge performance varies more than parameter counts suggest.

SAVRN Research, 2026-09-18

## Model Card

By PyTorch Image Models, published under mit, revision 81bd8f2ee563.

### Model card for edgenext_small.usi_in1k

An EdgeNeXt image classification model. Trained on ImageNet-1k by paper authors using distillation (USI as per Solving ImageNet).

### Model Details

- Model Type: Image classification / feature backbone
- Model Stats:
- Params (M): 5.6
- GMACs: 1.3
- Activations (M): 9.1
- Image size: train = 256 x 256, test = 320 x 320
- Papers:
- EdgeNeXt: Efficiently Amalgamated CNN-Transformer Architecture for Mobile Vision Applications: https://arxiv.org/abs/2206.10589
- Solving ImageNet: a Unified Scheme for Training any Backbone to Top Results: https://arxiv.org/abs/2204.03475
- Dataset: ImageNet-1k
- Original: https://github.com/mmaaz60/EdgeNeXt

### Model Usage

#### Image Classification

```
from urllib.request import urlopen
from PIL import Image
import timm

img = Image.open(urlopen(
    'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))

model = timm.create_model('edgenext_small.usi_in1k', pretrained=True)
model = model.eval()

# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)

output = model(transforms(img).unsqueeze(0))  # unsqueeze single image into batch of 1

top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
```

#### Feature Map Extraction

[Read the full model card (434 words)](https://savrn.com/models/edgenext-small-usi-in1k/card)

## Identity and Version

Repository

timm/edgenext_small.usi_in1k

Publisher

PyTorch Image Models

Task

Image classification

Modality

Image

Library

timm

Parameters

6M parameters

Languages

Not stated by the source

Revision

81bd8f2ee56330bdf6a7a2e47e1b2b82eb34f978

First published

2023-04-23

Last updated

2025-01-21

## Files and Weights

5 files, 44.8 MB in total. The weights are 2 files totalling 44.8 MB in bin, safetensors.

Weights2 files · 44.8 MB

Configuration1 file · 682 B

Documentation1 file · 4.4 KB

Repository1 file · 1.5 KB

Every file

| File | Type | Size | SHA-256 |
| --- | --- | --- | --- |
| model.safetensors | Weights | 22.4 MB | 14d824931ca7 |
| pytorch_model.bin | Weights | 22.4 MB | d5f9c753e704 |
| config.json | Configuration | 682 B | — |
| README.md | Documentation | 4.4 KB | — |
| .gitattributes | Repository | 1.5 KB | — |

## License and Download

License

mit

Access

Open weights, no gate

Download size

44.8 MB

[Download from PyTorch Image Models](https://huggingface.co/timm/edgenext_small.usi_in1k)

Released by PyTorch Image Models through its official repository on Hugging Face. [Read the license](https://opensource.org/license/mit).

## Built From

- Described by arXiv:2204.03475
- Described by arXiv:2206.10589
- Trained on (disclosed) imagenet-1k

## Memory Requirements

| Precision | Weights in memory |
| --- | --- |
| As published | 44.8 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 edgenext_small.usi_in1k

- [edgenext_small.usi_in1k vs mobilenetv3_small_100.lamb_in1k](https://savrn.com/models/compare/edgenext-small-usi-in1k-vs-mobilenetv3-small-100-lamb-in1k)

## Questions About edgenext_small.usi_in1k

### How much GPU memory does edgenext_small.usi_in1k need?

About 0 GB at 16-bit and 0 GB at 4-bit: the weights (6M parameters) plus a working margin. A long context needs more.

### What is the cheapest GPU to run edgenext_small.usi_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 edgenext_small.usi_in1k commercially?

Yes. edgenext_small.usi_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.

## Similar Models

Model · Image classification

### [vit_tiny_patch16_224.augreg_in21k_ft_in1k](https://savrn.com/models/vit-tiny-patch16-224-augreg-in21k-ft-in1k)

[PyTorch Image Models](https://savrn.com/model-publishers/timm)

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.

Open weights apache-2.0 6M parameters timm

[View model](https://savrn.com/models/vit-tiny-patch16-224-augreg-in21k-ft-in1k)

Model · Image classification

### [deit_tiny_patch16_224.fb_in1k](https://savrn.com/models/deit-tiny-patch16-224-fb-in1k)

[PyTorch Image Models](https://savrn.com/model-publishers/timm)

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.

Open weights apache-2.0 6M parameters timm

[View model](https://savrn.com/models/deit-tiny-patch16-224-fb-in1k)

Model · Image classification

### [efficientnet_b0.ra_in1k](https://savrn.com/models/efficientnet-b0-ra-in1k)

[PyTorch Image Models](https://savrn.com/model-publishers/timm)

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. 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.

Open weights apache-2.0 5M parameters timm

[View model](https://savrn.com/models/efficientnet-b0-ra-in1k)

Model · Image classification

### [cspnext_s.rsb_a1_in1k](https://savrn.com/models/cspnext-s-rsb-a1-in1k)

[Munehiro Kobayashi](https://savrn.com/model-publishers/munehiro-k)

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…

Open weights apache-2.0 5M parameters timm

[View model](https://savrn.com/models/cspnext-s-rsb-a1-in1k)

Model · Image classification

### [tf_mobilenetv3_large_minimal_100.in1k](https://savrn.com/models/tf-mobilenetv3-large-minimal-100-in1k)

[PyTorch Image Models](https://savrn.com/model-publishers/timm)

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.

Open weights apache-2.0 4M parameters timm

[View model](https://savrn.com/models/tf-mobilenetv3-large-minimal-100-in1k)

Model · Image classification

### [mobilenetv4_conv_small.e2400_r224_in1k](https://savrn.com/models/mobilenetv4-conv-small-e2400-r224-in1k)

[PyTorch Image Models](https://savrn.com/model-publishers/timm)

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

Open weights apache-2.0 4M parameters timm

[View model](https://savrn.com/models/mobilenetv4-conv-small-e2400-r224-in1k)

## PyTorch Image Models

[All models and datasets](https://savrn.com/model-publishers/timm)

## Versions

- [81bd8f2ee563](https://savrn.com/models/edgenext-small-usi-in1k/versions/81bd8f2ee563) · current 2026-09-18

## Explore More

- [All image classification models](https://savrn.com/models/tasks/image-classification)
- [All models under mit](https://savrn.com/models/licenses/mit)
- [Model comparisons](https://savrn.com/models/comparisons)
- [The model directory](https://savrn.com/models)
- [Open model prices by host](https://savrn.com/ai-index/pricing/open-models)

## Source

- Repository metadata, read 2026-10-20.
- [PyTorch Image Models website](https://github.com/huggingface/pytorch-image-models)
- [Hugging Face record](https://huggingface.co/timm/edgenext_small.usi_in1k)
- [How the hub is built](https://savrn.com/model-hub/methodology)