This is the model card of a transformers model that has been pushed on the Hub. Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Use the code below to get started with the model. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
Open-weight model · Image classification
convnext-tiny-finetuned-scenario16-2
by Ivan Richardson RichardsonI/convnext-tiny-finetuned-scenario16-2
convnext-tiny-finetuned-scenario16-2 is an open-weight model for image classification from Ivan Richardson. It has 28M parameters. At 16-bit it needs about 0.1 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index.
This is the model card of a transformers model that has been pushed on the Hub. Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Use the code below to get started with the model.
Parameters28M
Context—
Weights111.3 MB
License—
AccessOpen weights
Monthly Downloads—
Runs On
What it takes to serve convnext-tiny-finetuned-scenario16-2 (28M 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 | 0.1 GB | 0.1 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 5, 2026.
convnext-tiny-finetuned-scenario16-2 on every accelerator the SAVRN Index prices, at every precision
Model Card
This is the model card of a transformers model that has been pushed on the Hub. Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Use the code below to get started with the model. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
Excerpt from the card by Ivan Richardson.
Configuration
- Architecture
- ConvNextForImageClassification
- Model type
- convnext
Identity and Version
- Repository
- RichardsonI/convnext-tiny-finetuned-scenario16-2
- Publisher
- Ivan Richardson
- Task
- Image classification
- Modality
- Image
- Library
- transformers
- Parameters
- 28M parameters
- Languages
- Not stated by the source
- Revision
- 1939a4baecaf1738a87accdee1150fa6bf7ee89b
- First published
- 2026-10-02
- Last updated
- 2026-10-02
Files and Weights
8 files, 111.3 MB in total. The weights are 1 file totalling 111.3 MB in safetensors.
Weights1 file · 111.3 MB
Configuration3 files · 3.4 KB
Documentation1 file · 5.2 KB
Other2 files · 234 B
Repository1 file · 1.5 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 111.3 MB | fa1b7847a9bf |
| config.json | Configuration | 785 B | — |
| experiment_results/convnext_results.json | Configuration | 2.3 KB | — |
| preprocessor_config.json | Configuration | 352 B | — |
| README.md | Documentation | 5.2 KB | — |
| experiment_results/class_distribution.csv | Other | 87 B | — |
| experiment_results/hyperparameter_results.csv | Other | 147 B | — |
| .gitattributes | Repository | 1.5 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 111.3 MB
Download from Ivan Richardson
Released by Ivan Richardson through its official repository on Hugging Face.
Built From
- Described by arXiv:1910.09700
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 111.3 MB |
| 16-bit | 0.1 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 convnext-tiny-finetuned-scenario16-2
How much GPU memory does convnext-tiny-finetuned-scenario16-2 need?
About 0.1 GB at 16-bit and 0 GB at 4-bit: the weights (28M parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run convnext-tiny-finetuned-scenario16-2 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.
Similar Models
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-l8xb256-rsb-a1-600ein1k-6a760974.pth ImageNet-1k…
A Swin Transformer image classification model. Pretrained on ImageNet-1k by paper authors. Explore the dataset and runtime metrics of this model in timm model results.
A ConvNeXt image classification model. Pretrained in timm on ImageNet-12k (a 11821 class subset of full ImageNet-22k) and fine-tuned on ImageNet-1k by Ross Wightman. ImageNet-12k training done on TPUs thanks to support of the TRC program. Fine-tuning performed on 8x GPU Lambda Labs cloud instances. 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 ConvNeXt image classification model. Pretrained on ImageNet-22k and fine-tuned on ImageNet-1k by paper authors. 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 ConvNeXt-V2 image classification model. Pretrained with a fully convolutional masked autoencoder framework (FCMAE) and fine-tuned on ImageNet-22k and then 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.