timm AI Models

Approved models

54

Records published from this collection

Provider information

lab

Review approach

Verify each model’s source, terms, capabilities, and current availability

timm models in this directory cover image classification, image feature extraction, zero-shot image classification. Start with the task you need to solve, then open a model profile to check its recorded inputs, outputs, licensing and deployment options.

Models to explore

Choosing a model

Use held-out images that resemble deployment traffic, including lighting changes and confusing classes. Examine per-class precision and recall and confidence calibration rather than relying only on top-line accuracy.

Compare the right details

Check whether two entries describe distinct models or different hosted routes for the same model. Keep the checkpoint, host, test settings and evaluation date together. Missing prices and limits mean the directory has no recorded figure, not that use is free or unlimited.

Browse the AI model directory or compare two models.

timm model list

Review each record individually; collection membership does not imply a recommendation or guarantee of availability.

54 models
timm/convnext_base.clip_laion2b_augreg_ft_in12k_in1k
timm
10.0————
timm/convnext_base.dinov3_lvd1689m
timm
10.0————
timm/convnext_base.fb_in22k_ft_in1k
timm
10.0————
timm/convnext_base.fb_in22k_ft_in1k_384
timm
10.0————
timm/convnext_femto.d1_in1k
timm
10.0————
timm/convnext_small.fb_in22k_ft_in1k_384
timm
10.0————
timm/convnext_tiny.dinov3_lvd1689m
timm
10.0————
timm/convnext_tiny.fb_in22k_ft_in1k
timm
10.0————
timm/convnext_tiny.in12k_ft_in1k
timm
10.0————
timm/convnextv2_tiny.fcmae_ft_in22k_in1k
timm
10.0————
timm/densenet121.ra_in1k
timm
10.0————
timm/edgenext_small.usi_in1k
timm
10.0————
timm/efficientnet_b0.ra_in1k
timm
10.0————
timm/efficientnet_b2.ra_in1k
timm
10.0————
timm/efficientnet_b3.ra2_in1k
timm
10.0————
timm/mobilenetv3_large_100.ra_in1k
timm
10.0————
timm/mobilenetv3_small_100.lamb_in1k
timm
10.0————
timm/mobilenetv4_conv_small.e2400_r224_in1k
timm
10.0————
timm/naflexvit_so400m_patch16_siglip.v2_webli
timm
10.0————
timm/regnety_032.ra_in1k
timm
10.0————
timm/repvgg_a0.rvgg_in1k
timm
10.0————
timm/resnet18.a1_in1k
timm
10.0————
timm/resnet18.a3_in1k
timm
10.0————
timm/resnet34.a1_in1k
timm
10.0————
timm/resnet50.a1_in1k
timm
10.0————
timm/resnet50.fb_swsl_ig1b_ft_in1k
timm
10.0————
timm/swin_base_patch4_window12_384.ms_in22k_ft_in1k
timm
10.0————
timm/swin_tiny_patch4_window7_224.ms_in1k
timm
10.0————
timm/tf_efficientnetv2_s.in21k_ft_in1k
timm
10.0————
timm/vit_base_patch14_dinov2.lvd142m
timm
10.0————
timm/vit_base_patch14_reg4_dinov2.lvd142m
timm
10.0————
timm/vit_base_patch16_224.augreg_in21k_ft_in1k
timm
10.0————
timm/vit_base_patch16_224.augreg2_in21k_ft_in1k
timm
10.0————
timm/vit_base_patch16_224.dino
timm
10.0————
timm/vit_base_patch16_clip_224.openai
timm
10.0————
timm/vit_base_patch16_dinov3_qkvb.lvd1689m
timm
10.0————
timm/vit_base_patch16_dinov3.lvd1689m
timm
10.0————
timm/vit_base_patch16_plus_clip_240.laion400m_e31
timm
10.0————
timm/vit_base_patch8_224.augreg2_in21k_ft_in1k
timm
10.0————
timm/vit_large_patch14_dinov2.lvd142m
timm
10.0————
timm/vit_large_patch14_reg4_dinov2.lvd142m
timm
10.0————
timm/vit_large_patch16_224.mae
timm
10.0————
timm/vit_large_patch16_dinov3.lvd1689m
timm
10.0————
timm/vit_large_patch16_siglip_256.v2_webli
timm
10.0————
timm/vit_small_patch14_dinov2.lvd142m
timm
10.0————
timm/vit_small_patch14_reg4_dinov2.lvd142m
timm
10.0————
timm/vit_small_patch16_224.augreg_in21k_ft_in1k
timm
10.0————
timm/vit_small_patch16_224.dino
timm
10.0————
timm/vit_small_patch16_dinov3.lvd1689m
timm
10.0————
timm/vit_so400m_patch16_siglip_256.v2_webli
timm
10.0————
timm/vit_so400m_patch16_siglip_512.v2_webli
timm
10.0————
timm/vit_tiny_patch16_224.augreg_in21k_ft_in1k
timm
10.0————
timm/vit_tiny_r_s16_p8_224.augreg_in21k
timm
10.0————
timm/wide_resnet50_2.racm_in1k
timm
10.0————

1–54 of 54 models · select a column to sort

About this order: Recommended shows our editorial shortlist first, followed by recent releases. The spec score is a 0–100 figure SyncDev calculates from each vendor's published specifications — context window, reasoning support, input modalities, tool calling, maximum output and how recently the model shipped. It measures breadth of capability, not benchmark performance, so a higher-scoring model is not automatically the better choice for your task.

About timm models

It groups source-backed directory records for research and comparison. Review each model page and its primary documentation because collection membership alone does not prove quality, availability, or suitability.