EfficientNetV2-L (torchvision efficientnetv2l) fine-tuned for the Perturb subnet (netuid 26).
Open-weight model · Image classification
gvision-adv-uid146
by Nguyễn Trung Kiên kiennt120/gvision-adv-uid146
gvision-adv-uid146 is an open-weight model for image classification from Nguyễn Trung Kiên, released under Apache License 2.0. It has 119M parameters. At 16-bit it needs about 0.3 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index.
EfficientNetV2-L (torchvision efficientnetv2l) fine-tuned for the Perturb subnet (netuid 26).
Parameters119M
Context—
Weights476.3 MB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads—
Runs On
What it takes to serve gvision-adv-uid146 (119M 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 | 0.3 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 | 0.1 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 18, 2026.
gvision-adv-uid146 on every accelerator the SAVRN Index prices, at every precision
Model Card
By Nguyễn Trung Kiên, published under apache-2.0, revision a7a5767f4eea.
EfficientNetV2-L (torchvision efficientnetv2l) fine-tuned for the Perturb subnet (netuid 26).
Read Nguyễn Trung Kiên's full model card
EfficientNetV2-L (torchvision efficientnet_v2_l) fine-tuned for the Perturb subnet (netuid 26).
- miner hotkey:
5CfnCqPFPqio7zF1Hh5UJ1VPRrPjT1caNpd9Nvyj8eDQzf2t - on-chain hash: sha256(model.safetensors || hotkey) =
09db3200fde97368c593a58354a19c189bec113fe67e00ccd6c363694b41482a
Identity and Version
- Repository
- kiennt120/gvision-adv-uid146
- Publisher
- Nguyễn Trung Kiên
- Task
- Image classification
- Modality
- Image
- Library
- torchvision
- Parameters
- 119M parameters
- Languages
- Not stated by the source
- Revision
- a7a5767f4eea567245936a446c1c521c8a01975a
- First published
- 2026-09-23
- Last updated
- 2026-09-23
Files and Weights
4 files, 476.3 MB in total. The weights are 1 file totalling 476.3 MB in safetensors.
Weights1 file · 476.3 MB
Configuration1 file · 565 B
Documentation1 file · 459 B
Repository1 file · 1.5 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 476.3 MB | 1c6f2102772a |
| config.json | Configuration | 565 B | — |
| README.md | Documentation | 459 B | — |
| .gitattributes | Repository | 1.5 KB | — |
License and Download
- License
- apache-2.0
- Access
- Open weights, no gate
- Download size
- 476.3 MB
Download from Nguyễn Trung Kiên
Released by Nguyễn Trung Kiên through its official repository on Hugging Face. Read the license.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 476.3 MB |
| 16-bit | 0.2 GB |
| 8-bit | 0.1 GB |
| 4-bit | 0.1 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About gvision-adv-uid146
How much GPU memory does gvision-adv-uid146 need?
About 0.3 GB at 16-bit and 0.1 GB at 4-bit: the weights (119M parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run gvision-adv-uid146 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 gvision-adv-uid146 commercially?
Yes. gvision-adv-uid146 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
EfficientNetV2-L (torchvision efficientnetv2l, 1000 ImageNet classes) fine-tuned with adversarial training for the Perturb subnet (netuid 26).
Built with DINOv3. This is the completed V2 mean-pooling model for 2,991 plant species from Western Australia. Supply one photo, or 2–4 distinct photos from the same plant observation. This release uses the epoch-12 EMA weights from the expanded-data BF16 training run. The CLI uses self-contained TorchScript graphs (encoder.ts and classifier.ts) and imports no project modules. FP32 model.safetensors is also included for research use. Optimizer state and training data are excluded. executorch/PlantDetect-WA-V2-INT8.pte is a W8A8 export of this mean-pooling checkpoint for CPU inference without PyTorch. It uses custom plantquant:: kernels (INT8 weights with per-output-channel FP32 scales, FP16…
A BEiT-v2 image classification model. Trained on ImageNet-1k with self-supervised masked image modelling (MIM) using a VQ-KD encoder as a visual tokenizer (via OpenAI CLIP B/16 teacher). Fine-tuned on ImageNet-22k. - 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.
A Vision Transformer (ViT) image classification model. Trained on ImageNet-21k (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.
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