# convnextv2-tiny-22k-224 by AI at Meta: Open-Weight Model Source: https://savrn.com/models/convnextv2-tiny-22k-224 Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- ## Runs On What it takes to serve convnextv2-tiny-22k-224 (29M 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](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. [convnextv2-tiny-22k-224 on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/convnextv2-tiny-22k-224/gpus) ## Model Card By AI at Meta, published under apache-2.0, revision 9cba4896e97b. ### ConvNeXt V2 (tiny-sized model) ConvNeXt V2 model pretrained using the FCMAE framework and fine-tuned on the ImageNet-22K dataset at resolution 224x224. It was introduced in the paper [ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders](https://savrn.com/papers/convnext-v2-co-designing-and-scaling-convnets-with-masked-autoencoders) by Woo et al. and first released in [this repository](https://github.com/facebookresearch/ConvNeXt-V2). Disclaimer: The team releasing ConvNeXT V2 did not write a model card for this model so this model card has been written by the Hugging Face team. ### Model description ConvNeXt V2 is a pure convolutional model (ConvNet) that introduces a fully convolutional masked autoencoder framework (FCMAE) and a new Global Response Normalization (GRN) layer to ConvNeXt. ConvNeXt V2 significantly improves the performance of pure ConvNets on various recognition benchmarks. ### Intended uses & limitations You can use the raw model for image classification. See the [model hub](https://huggingface.co/models?search=convnextv2) to look for fine-tuned versions on a task that interests you. #### How to use [Read the full model card (305 words)](https://savrn.com/models/convnextv2-tiny-22k-224/card) ## Configuration Architecture ConvNextV2ForImageClassification Stored precision float32 Model type convnextv2 ## Identity and Version Repository facebook/convnextv2-tiny-22k-224 Publisher AI at Meta Task Image classification Modality Image Library transformers Parameters 29M parameters Languages tf Revision 9cba4896e97bb86b1eb609e482a2149d84f345bc First published 2023-02-19 Last updated 2025-02-17 ## Files and Weights 7 files, 344.0 MB in total. The weights are 3 files totalling 344.0 MB in bin, h5, safetensors. Weights3 files · 344.0 MB Configuration2 files · 70.1 KB Documentation1 file · 3.4 KB Repository1 file · 1.5 KB Every file | File | Type | Size | SHA-256 | | --- | --- | --- | --- | | model.safetensors | Weights | 114.6 MB | b33653bb8c06 | | pytorch_model.bin | Weights | 114.6 MB | e5c2aa493ada | | tf_model.h5 | Weights | 114.8 MB | c46352c572fd | | config.json | Configuration | 69.7 KB | — | | preprocessor_config.json | Configuration | 352 B | — | | README.md | Documentation | 3.4 KB | — | | .gitattributes | Repository | 1.5 KB | — | ## License and Download License apache-2.0 Access Open weights, no gate Download size 344.0 MB [Download from AI at Meta](https://huggingface.co/facebook/convnextv2-tiny-22k-224) Released by AI at Meta through its official repository on Hugging Face. [Read the license](https://www.apache.org/licenses/LICENSE-2.0). ## Built From - Described by [arXiv:2301.00808](https://savrn.com/papers/convnext-v2-co-designing-and-scaling-convnets-with-masked-autoencoders) - Trained on (disclosed) imagenet-22k ## Memory Requirements | Precision | Weights in memory | | --- | --- | | As published | 344.0 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 convnextv2-tiny-22k-224 ### How much GPU memory does convnextv2-tiny-22k-224 need? About 0.1 GB at 16-bit and 0 GB at 4-bit: the weights (29M parameters) plus a working margin. A long context needs more. ### What is the cheapest GPU to run convnextv2-tiny-22k-224 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 convnextv2-tiny-22k-224 commercially? Yes. convnextv2-tiny-22k-224 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_tiny.fcmae_ft_in22k_in1k](https://savrn.com/models/convnextv2-tiny-fcmae-ft-in22k-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-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. Open weights cc-by-nc-4.0 29M parameters timm [View model](https://savrn.com/models/convnextv2-tiny-fcmae-ft-in22k-in1k) Model · Image classification ### [convnext_tiny.in12k_ft_in1k](https://savrn.com/models/convnext-tiny-in12k-ft-in1k) [PyTorch Image Models](https://savrn.com/model-publishers/timm) 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. Open weights apache-2.0 29M parameters timm [View model](https://savrn.com/models/convnext-tiny-in12k-ft-in1k) Model · Image classification ### [convnext_tiny.fb_in22k_ft_in1k](https://savrn.com/models/convnext-tiny-fb-in22k-ft-in1k) [PyTorch Image Models](https://savrn.com/model-publishers/timm) 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. Open weights apache-2.0 29M parameters timm [View model](https://savrn.com/models/convnext-tiny-fb-in22k-ft-in1k) Model · Image classification ### [swin_tiny_patch4_window7_224.ms_in1k](https://savrn.com/models/swin-tiny-patch4-window7-224-ms-in1k) [PyTorch Image Models](https://savrn.com/model-publishers/timm) 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. Open weights mit 29M parameters timm [View model](https://savrn.com/models/swin-tiny-patch4-window7-224-ms-in1k) Model · Image classification ### [convnext-tiny-finetuned-scenario16](https://savrn.com/models/convnext-tiny-finetuned-scenario16) [Ivan Richardson](https://savrn.com/model-publishers/richardsoni) 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 weights 28M parameters transformers [View model](https://savrn.com/models/convnext-tiny-finetuned-scenario16) Model · Image classification ### [convnext-tiny-finetuned-scenario16-2](https://savrn.com/models/convnext-tiny-finetuned-scenario16-2) [Ivan Richardson](https://savrn.com/model-publishers/richardsoni) 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 weights 28M parameters transformers [View model](https://savrn.com/models/convnext-tiny-finetuned-scenario16-2) ## AI at Meta [All models and datasets](https://savrn.com/model-publishers/facebook) ## Versions - [9cba4896e97b](https://savrn.com/models/convnextv2-tiny-22k-224/versions/9cba4896e97b) · 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. - [AI at Meta website](https://ai.meta.com/resources/models-and-libraries/) - [Hugging Face record](https://huggingface.co/facebook/convnextv2-tiny-22k-224) - [How the hub is built](https://savrn.com/model-hub/methodology)