laya-vision-smolvlm2-256m-split1024

thaitea/laya-vision-smolvlm2-256m-split1024

Visual Question Answering237M parameterslayaLicense: cc-by-nc-4.0

Tracked by OpenModelStats since September 23, 2026View on Hugging Face ↗

Downloads 30D: 0
Total downloads: 0
Gained 7D: —
Gained 30D: —
Likes: 0
Rank · tracked models: —; –this week
Parameters: 237M
Last source update: Sep 22, 2026

7D 30D 90D 1Y All

Total downloads Gained per day Rolling recent downloads

Downloads over time

Rolling recent-window downloads as reported

Likes over time

Rank among tracked models

Lower is better

Not enough tracked history yet for a chart.

OpenModelStats began tracking this model on 2026-09-23. Charts appear as daily observations accumulate.

Overview

laya-vision-smolvlm2-256m-split1024 is a visual question answering model published by thaitea. OpenModelStats has tracked the model since Sep 23, 2026, most recently observing it Sep 24, 2026.

Published: Sep 22, 2026
Last updated: Sep 22, 2026
Library: laya
License: cc-by-nc-4.0
Task: Visual Question Answering
Parameters: 236,562,310
Spaces: —
Derivative models: —
Velocity 7D/day: —

layasafetensorscalibrationdecision-modelvisionsmolvlmvisual-question-answeringendataset:HuggingFaceM4/the_cauldronbase_model:HuggingFaceTB/SmolVLM2-256M-Video-Instructbase_model:finetune:HuggingFaceTB/SmolVLM2-256M-Video-Instructlicense:cc-by-nc-4.0

Publisher

thaiteaView publisher statistics →

Derived from HuggingFaceTB/SmolVLM2-256M-Video-Instruct (reported by the source; parent not yet tracked).

Similar models

Models similar to laya-vision-smolvlm2-256m-split1024
Model	Task	DL 30D	Likes	Params
laya-visionthaitea	Visual Question Answering	0	36	201M
deplotgoogle	Visual Question Answering	19.5K	323	282M
pix2struct-docvqa-basegoogle	Visual Question Answering	1,631	44	282M
pix2struct-ai2d-basegoogle	Visual Question Answering	1,020	43	282M
TinyDoc-VLM-256Meulogik	Visual Question Answering	437	7	290M
git-base-vqav2microsoft	Visual Question Answering	1,244	21	177M