Model reference · open weights
openvision-vit-small-patch16-224 is an open-weight embedding model from UCSC-VLAA. openvision-vit-small-patch16-224 (BF16) weighs 222 MB; the smallest configuration that runs it is RTX 3060 12 GB.
What it is
| Released by | UCSC-VLAA |
|---|---|
| Released | 2025-05-06 |
| VRAM | 222 MB for the weights |
What it runs on
| Card | Runs | Memory |
|---|---|---|
| RTX 3060 12 GB | fits | 11.6 GB |
| RTX 4060 Ti 16 GB | fits | 15.4 GB |
| RTX 3090 24 GB | fits | 23.4 GB |
| RTX 4090 24 GB | fits | 23.4 GB |
| RTX 5090 32 GB | fits | 31.0 GB |
| L40S 48 GB | fits | 44.0 GB |
| A100 80 GB | fits | 78.2 GB |
| H100 80 GB | fits | 78.1 GB |
| RTX PRO 6000 Blackwell 96 GB | fits | 93.8 GB |
| DGX Spark (GB10) 128 GB unified | fits | 107 GB |
| H200 141 GB | fits | 138 GB |
| B200 180 GB | fits | 176 GB |
From the model card
This repository contains the OpenVision vision encoders described in the paper OpenVision: A Fully-Open, Cost-Effective Family of Advanced Vision Encoders for Multimodal Learning.
Project page: https://ucsc-vlaa.github.io/OpenVision
Code: https://github.com/UCSC-VLAA/OpenVision
Quoted from the model card on Hugging Face. The full card is behind the Hugging Face link above.
How it works