SAVRN
Search Contact SAVRN

Open-weight model

mivolo_v2

by Irina Tolstykh iitolstykh/mivolo_v2

We introduce state-of-the-art multi-input transformer for age and gender estimation. This model was trained on proprietary and open-source datasets.

Parameters29M
Context
Weights115.1 MB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads2.7M

Runs On

What it takes to serve mivolo_v2 (29M parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.

PrecisionWeightsMemory neededCheapest setupPer hourAlso 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 Sep 18, 2026.

SAVRN's Notes on mivolo_v2

Point it at a photo and it hands back an age and a gender, the entire job for Irina Tolstykh's 29M-parameter multi-input transformer. At 16-bit the weights take 0.1 GB, and the 8-bit and 4-bit rows round to zero, yet the cheapest setup is a 192 GB MI300X at $1.85 per hour. The card is the cost and the model a rounding error, so batch images to fill it or share it with something bigger.

Apache 2.0 permits commercial use, modification and redistribution, with license, copyright and NOTICE files kept, changes stated, plus a patent grant. Check the pinned stack, mivolo with transformers 4.51.0 and accelerate 1.8.1, and ask about the training data, a mix of proprietary and open-source sets the publisher does not name. No Index host serves it by the token, and 2,687,640 monthly downloads against 32 likes says pipelines pull this, not people.

Model Card

By Irina Tolstykh, published under apache-2.0, revision 53393526c220.

Model Card for MiVOLO V2 model

Read the full model card (318 words)

Configuration

Architecture
MiVOLOForImageClassification
Stored precision
float16
Model type
mivolo

Identity and Version

Repository
iitolstykh/mivolo_v2
Publisher
Irina Tolstykh
Task
Not stated by the source
Modality
Other
Library
mivolo
Parameters
29M parameters
Languages
Not stated by the source
Revision
53393526c220e34cdd7b722b36d22b6f9e5f4241
First published
2024-03-05
Last updated
2026-03-11

Files and Weights

10 files, 115.1 MB in total. The weights are 1 file totalling 115.1 MB in safetensors.

Weights1 file · 115.1 MB
Configuration5 files · 9.2 KB
Documentation1 file · 3.8 KB
Other2 files · 35.4 KB
Repository1 file · 1.6 KB
Every file
FileTypeSizeSHA-256
model.safetensorsWeights115.1 MB 96efb47051c0
config.jsonConfiguration924 B
configuration_mivolo.pyConfiguration1.5 KB
mivolo_image_processor.pyConfiguration1.5 KB
modeling_mivolo.pyConfiguration5.3 KB
preprocessor_config.jsonConfiguration96 B
README.mdDocumentation3.8 KB
icon.jpgOther35.3 KB
requirements.txtOther150 B
.gitattributesRepository1.6 KB

License and Download

License
apache-2.0
Access
Open weights, no gate
Download size
115.1 MB
Download from Irina Tolstykh

Released by Irina Tolstykh through its official repository on Hugging Face. Read the license.

Built From

Memory Requirements

PrecisionWeights in memory
As published115.1 MB
16-bit0.1 GB
8-bit0.0 GB
4-bit0.0 GB

Weights only, from the published parameter count; the key-value cache and runtime add to this.

Questions About mivolo_v2

How much GPU memory does mivolo_v2 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 mivolo_v2 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 mivolo_v2 commercially?

Yes. mivolo_v2 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.