# densenet121.ra_in1k by PyTorch Image Models: Open Model
Source: https://savrn.com/models/densenet121-ra-in1k
Markdown alternate of the page above; the site index is https://savrn.com/llms.txt

---

## Runs On

What it takes to serve densenet121.ra_in1k (8M 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.

[densenet121.ra_in1k on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/densenet121-ra-in1k/gpus)

## Model Card

By PyTorch Image Models, published under apache-2.0, revision 92007b6200e0.

### Model card for densenet121.ra_in1k

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](https://savrn.com/papers/resnet-strikes-back-an-improved-training-procedure-in-timm).

### Model Details

- Model Type: Image classification / feature backbone
- Model Stats:
- Params (M): 8.0
- GMACs: 2.9
- Activations (M): 6.9
- Image size: train = 224 x 224, test = 288 x 288
- Papers:
- Densely Connected Convolutional Networks: https://arxiv.org/abs/1608.06993
- 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

```
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('densenet121.ra_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 (384 words)](https://savrn.com/models/densenet121-ra-in1k/card)

## Identity and Version

Repository

timm/densenet121.ra_in1k

Publisher

PyTorch Image Models

Task

Image classification

Modality

Image

Library

timm

Parameters

8M parameters

Languages

Not stated by the source

Revision

92007b6200e0b4a4fe68cb4e3947022a928aaaae

First published

2023-04-21

Last updated

2025-01-21

## Files and Weights

5 files, 64.9 MB in total. The weights are 2 files totalling 64.9 MB in bin, safetensors.

Weights2 files · 64.9 MB

Configuration1 file · 668 B

Documentation1 file · 4.0 KB

Repository1 file · 1.5 KB

Every file

| File | Type | Size | SHA-256 |
| --- | --- | --- | --- |
| model.safetensors | Weights | 32.3 MB | eae900d8ae5b |
| pytorch_model.bin | Weights | 32.5 MB | e73d2a763b34 |
| config.json | Configuration | 668 B | — |
| README.md | Documentation | 4.0 KB | — |
| .gitattributes | Repository | 1.5 KB | — |

## License and Download

License

apache-2.0

Access

Open weights, no gate

Download size

64.9 MB

[Download from PyTorch Image Models](https://huggingface.co/timm/densenet121.ra_in1k)

Released by PyTorch Image Models through its official repository on Hugging Face. [Read the license](https://www.apache.org/licenses/LICENSE-2.0).

## Built From

- Described by arXiv:1608.06993
- Described by [arXiv:2110.00476](https://savrn.com/papers/resnet-strikes-back-an-improved-training-procedure-in-timm)
- Trained on (disclosed) imagenet-1k

## Memory Requirements

| Precision | Weights in memory |
| --- | --- |
| As published | 64.9 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.

## Questions About densenet121.ra_in1k

### How much GPU memory does densenet121.ra_in1k need?

About 0 GB at 16-bit and 0 GB at 4-bit: the weights (8M parameters) plus a working margin. A long context needs more.

### What is the cheapest GPU to run densenet121.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 densenet121.ra_in1k commercially?

Yes. densenet121.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

Model · Image classification

### [convnextv2_pico.fcmae_ft_in1k](https://savrn.com/models/convnextv2-pico-fcmae-ft-in1k)

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

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.

Open weights cc-by-nc-4.0 9M parameters timm

[View model](https://savrn.com/models/convnextv2-pico-fcmae-ft-in1k)

Model · Image classification

### [repvgg_a0.rvgg_in1k](https://savrn.com/models/repvgg-a0-rvgg-in1k)

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

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.

Open weights mit 9M parameters timm

[View model](https://savrn.com/models/repvgg-a0-rvgg-in1k)

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

### [edgenext_small.usi_in1k](https://savrn.com/models/edgenext-small-usi-in1k)

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

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](https://savrn.com/models/edgenext-small-usi-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)

## PyTorch Image Models

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

## Versions

- [92007b6200e0](https://savrn.com/models/densenet121-ra-in1k/versions/92007b6200e0) · current 2026-09-18

## Explore More

- [All image classification models](https://savrn.com/models/tasks/image-classification)
- [All models under apache-2.0](https://savrn.com/models/licenses/apache-2-0)
- [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/densenet121.ra_in1k)
- [How the hub is built](https://savrn.com/model-hub/methodology)