alt.freeweights.* · 29 sections · 8900 models listed (2868 shown under their base as variants)
alt.freeweights.vision
Image classification, detection, segmentation, CLIP, ViT and SigLIP models, time-series models and classic encoder models. 1225 models, best first. Order is never for sale.
1225 models
SubjectSizeParamsLicenseDate
openMaMMUT-ViT-L-14-512x512-pt_datacomp1b-ft_DFN512x512-s293M-b32kHosted (signed) From: laion in alt.freeweights.vision6.12 GB—Permissive2026-11-14openMaMMUT-ViT-B-32-512x512-pt_DFN2B-ft_DFN512x512-s293M-b73kHosted (signed) From: laion in alt.freeweights.vision2.20 GB—Permissive2026-11-14ViCLIP-L-14-BVD-V-50M-s50M-b32KHosted (signed) From: laion in alt.freeweights.vision6.85 GB428MPermissive2026-11-14dinov3-vitl16-pretrain-lvd1689mFrom the publisher From: facebook in alt.freeweights.vision1.21 GB303MGated2026-11-15dinov3-vitb16-pretrain-lvd1689mFrom the publisher From: facebook in alt.freeweights.vision343 MB86MGated2026-11-15dinov3-vits16-pretrain-lvd1689mFrom the publisher From: facebook in alt.freeweights.vision86.4 MB22MGated2026-11-15Slide, drag, or use the arrow keys.
No model matches these filters.Remove a filter or search for something shorter.
Every row is downloadable or links to its source.