Search public pages, research tools, and SAVRN solutions.
Open-weight model · Image classification
by Prithiv Sakthi prithivMLmods/Gender-Classifier-Mini
Gender-Classifier-Mini is an open-weight model for image classification from Prithiv Sakthi, released under Apache License 2.0. It has 93M parameters and a 64-token context. At 16-bit it needs about 0.2 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index. It draws 1.1M downloads a month.
The model categorizes images into two classes: The Gender-Classifier-Mini model is designed to classify images into gender categories. Potential use cases include
What it takes to serve Gender-Classifier-Mini (93M 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 | 0.2 GB | 0.2 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 0.1 GB | 0.1 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 0.0 GB | 0.1 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 7, 2026.
Gender-Classifier-Mini on every accelerator the SAVRN Index prices, at every precision
By Prithiv Sakthi, published under apache-2.0, revision 4855356b698e.
Gender-Classifier-Mini is an image classification vision-language encoder model fine-tuned from google/siglip2-base-patch16-224 for a single-label classification task. It is designed to classify images based on gender using the SiglipForImageClassification architecture.
Accuracy: 0.9720
F1 Score: 0.9720
Classification Report:
precision recall f1-score support
Female 0.9660 0.9796 0.9727 2549
Male 0.9785 0.9641 0.9712 2451
accuracy 0.9720 5000
macro avg 0.9722 0.9718 0.9720 5000
weighted avg 0.9721 0.9720 0.9720 5000
The model categorizes images into two classes: - Class 0:"Female " -Class 1:"Male "
!pip install -q transformers torch pillow gradio
22 files, 2.5 GB in total. The weights are 12 files totalling 2.5 GB in bin, pt, pth, safetensors.
| File | Type | Size | SHA-256 |
|---|---|---|---|
| checkpoint-157/model.safetensors | Weights | 371.6 MB | 4b3c881ec1fe |
| checkpoint-157/optimizer.pt | Weights | 686.6 MB | 7e42ca610964 |
| checkpoint-157/rng_state.pth | Weights | 14.2 KB | 86d5603fb947 |
| checkpoint-157/scheduler.pt | Weights | 1.1 KB | a4e52ea24361 |
| checkpoint-157/training_args.bin | Weights | 5.3 KB | 60bfe4936cb8 |
| checkpoint-314/model.safetensors | Weights | 371.6 MB | 672245c638f4 |
| checkpoint-314/optimizer.pt | Weights | 686.6 MB | ca2c61bce314 |
| checkpoint-314/rng_state.pth | Weights | 14.2 KB | 1d268ac255a6 |
| checkpoint-314/scheduler.pt | Weights | 1.1 KB | 8b7714de4736 |
| checkpoint-314/training_args.bin | Weights | 5.3 KB | 60bfe4936cb8 |
| model.safetensors | Weights | 371.6 MB | 672245c638f4 |
| training_args.bin | Weights | 5.3 KB | 60bfe4936cb8 |
| checkpoint-157/config.json | Configuration | 1.1 KB | — |
| checkpoint-157/preprocessor_config.json | Configuration | 394 B | — |
| checkpoint-157/trainer_state.json | Configuration | 1.1 KB | — |
| checkpoint-314/config.json | Configuration | 1.1 KB | — |
| checkpoint-314/preprocessor_config.json | Configuration | 394 B | — |
| checkpoint-314/trainer_state.json | Configuration | 1.4 KB | — |
| config.json | Configuration | 1.1 KB | — |
| preprocessor_config.json | Configuration | 394 B | — |
| README.md | Documentation | 3.1 KB | — |
| .gitattributes | Repository | 1.5 KB | — |
Released by Prithiv Sakthi through its official repository on Hugging Face. Read the license.
| Precision | Weights in memory |
|---|---|
| As published | 2.5 GB |
| 16-bit | 0.2 GB |
| 8-bit | 0.1 GB |
| 4-bit | 0.0 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
About 0.2 GB at 16-bit and 0.1 GB at 4-bit: the weights (93M parameters) plus a working margin. A long context needs more.
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.
Yes. Gender-Classifier-Mini 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.
64 tokens, from the maximum position embeddings in its published configuration.
SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features https://arxiv.org/pdf/2502.14786 The model classifies each image into one of the following content categories: This model is intended for applications such as
A Swin Transformer 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.
ConvNeXt V2 model pretrained using the FCMAE framework and fine-tuned on the ImageNet-22K dataset at resolution 384x384. It was introduced in the paper ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders by Woo et al. and first released in this repository. 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. 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…
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.
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 image classification model. CLIP image tower weights pretrained in OpenCLIP on LAION and fine-tuned on ImageNet-12k followed by ImageNet-1k in timm bby Ross Wightman. Please see related OpenCLIP model cards for more details on pretrain: https://huggingface.co/laion/CLIP-convnextxxlarge-laion2B-s34B-b82K-augreg-soup https://huggingface.co/laion/CLIP-convnextlarged.laion2B-s26B-b102K-augreg https://huggingface.co/laion/CLIP-convnextbasew-laion2B-s13B-b82K-augreg https://huggingface.co/laion/CLIP-convnextbasew320-laionaesthetic-s13B-b82K - Learning Transferable Visual Models From Natural Language Supervision: https://arxiv.org/abs/2103.00020 Explore the dataset and runtime metrics…