Model reference · open weights

vit_base_patch16_siglip_384.webli

Embeddings timm Image embed 1 build Open weights 642 dl/mo

vit_base_patch16_siglip_384.webli is an open-weight embedding model from timm. vit_base_patch16_siglip_384.webli (FP32) weighs 186 MB; the smallest configuration that runs it is RTX 3060 12 GB.

What it is

Released bytimm
Released2024-12-24
Parameters93M
VRAM186 MB for the weights

What it runs on

Memory and cards for vit_base_patch16_siglip_384.webli (FP32)

186 MBweights, file size
1.1 GBruntime overhead
CardRunsMemory
RTX 3060 12 GBfits11.6 GB
RTX 4060 Ti 16 GBfits15.4 GB
RTX 3090 24 GBfits23.4 GB
RTX 4090 24 GBfits23.4 GB
RTX 5090 32 GBfits31.0 GB
L40S 48 GBfits44.0 GB
A100 80 GBfits78.2 GB
H100 80 GBfits78.1 GB
RTX PRO 6000 Blackwell 96 GBfits93.8 GB
DGX Spark (GB10) 128 GB unifiedfits107 GB
H200 141 GBfits138 GB
B200 180 GBfits176 GB

From the model card

What timm says about vit_base_patch16_siglip_384.webli

timm SigLIP (image encoder only, with original attention pooling) weights from https://huggingface.co/timm/ViT-B-16-SigLIP-384

Quoted from the model card on Hugging Face. The full card is behind the Hugging Face link above.

How it works

How embedding models work

Your textsentence / documentEncodermaps meaningVectorlist of numbersAn embedding model turns text into a vector, so similar meanings sit close together, which is the basis of search and RAG.
© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms