mobilenetv4_conv_small.e2400_r224_in1k by PyTorch Image Models

Runs On

What it takes to serve mobilenetv4_conv_small.e2400_r224_in1k (4M parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.

Precision	Cheapest setup	Per hour	Also fits
16-bit	1x MI300X (192 GB) Vultr	$1.85	1x H100 $1.99 · 1x MI325X $2.00
8-bit	1x MI300X (192 GB) Vultr	$1.85	1x H100 $1.99 · 1x MI325X $2.00
4-bit	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 16, 2026.

mobilenetv4_conv_small.e2400_r224_in1k on every accelerator the SAVRN Index prices, at every precision

Model Card

By PyTorch Image Models, published under apache-2.0, revision 331fb8037795.

Model card for mobilenetv4_conv_small.e2400_r224_in1k

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.

Model Details

Model Type: Image classification / feature backbone
Model Stats:
Params (M): 3.8
GMACs: 0.2
Activations (M): 2.0
Image size: train = 224 x 224, test = 256 x 256
Dataset: ImageNet-1k
Original: https://github.com/tensorflow/models/tree/master/official/vision
Papers:
MobileNetV4 -- Universal Models for the Mobile Ecosystem: https://arxiv.org/abs/2404.10518
PyTorch Image Models: https://github.com/huggingface/pytorch-image-models

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('mobilenetv4_conv_small.e2400_r224_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 (666 words)

Identity and Version

Repository: timm/mobilenetv4_conv_small.e2400_r224_in1k
Publisher: PyTorch Image Models
Task: Image classification
Modality: Image
Library: timm
Parameters: 4M parameters
Languages: Not stated by the source
Revision: 331fb803779522b685cf942e15f914fb6741c1eb
First published: 2024-06-16
Last updated: 2025-01-21

Files and Weights

5 files, 30.5 MB in total. The weights are 2 files totalling 30.5 MB in bin, safetensors.

Weights2 files · 30.5 MB

Configuration1 file · 681 B

Documentation1 file · 13.1 KB

Repository1 file · 1.5 KB

Every file

File	Type	Size	SHA-256
model.safetensors	Weights	15.2 MB	7a7102ec18f6
pytorch_model.bin	Weights	15.3 MB	28f2109728e2
config.json	Configuration	681 B	—
README.md	Documentation	13.1 KB	—
.gitattributes	Repository	1.5 KB	—

License and Download

License: apache-2.0
Access: Open weights, no gate
Download size: 30.5 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:2404.10518
Trained on (disclosed) imagenet-1k

Memory Requirements

Precision	Weights in memory
As published	30.5 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 mobilenetv4_conv_small.e2400_r224_in1k

mobilenetv3_small_100.lamb_in1k vs mobilenetv4_conv_small.e2400_r224_in1k

Questions About mobilenetv4_conv_small.e2400_r224_in1k

How much GPU memory does mobilenetv4_conv_small.e2400_r224_in1k need?

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

What is the cheapest GPU to run mobilenetv4_conv_small.e2400_r224_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 mobilenetv4_conv_small.e2400_r224_in1k commercially?

Yes. mobilenetv4_conv_small.e2400_r224_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

Model · Image classification

tf_mobilenetv3_large_minimal_100.in1k

PyTorch Image Models

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

Model · Image classification

cspnext_tiny.rsb_a1_in1k

Munehiro Kobayashi

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-tinyimagenet600e-3a2dd350.pth ImageNet-1k…

Open weights apache-2.0 3M parameters timm

View model

Model · Image classification

cspnext_s.rsb_a1_in1k

Munehiro Kobayashi

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

Model · Image classification

mobilenetv3_small_100.lamb_in1k

PyTorch Image Models

A MobileNet-v3 image classification model. Trained on ImageNet-1k in timm using recipe template described below. A LAMB optimizer based recipe that is similar to ResNet Strikes Back A2 but 50% longer with EMA weight averaging, no CutMix 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 3M parameters timm

View model

Model · Image classification

efficientnet_b0.ra_in1k

PyTorch Image Models

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

Model · Image classification

edgenext_small.usi_in1k

PyTorch Image Models

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

Open weights mit 6M parameters timm

View model