tf_efficientnetv2_s.in21k_ft_in1k vs efficientnet_b3.ra2_in1k
Specs, VRAM requirements and download trends — updated 7 November 2026.
timm · A · Open weights
Params
20 M
Context
—
30d
3.6 M
apache-2.0 · commercial OK
timm · B · Open weights
Params
10 M
Context
—
30d
242 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | tf_efficientnetv2_s.in21k_ft_in1k | efficientnet_b3.ra2_in1k |
|---|---|---|
| Parameters | 20 M | 10 M |
| Architecture | — | — |
| Context length | — | — |
| Licence | apache-2.0 | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | — | — |
| Downloads 30d | 3,649,958 | 242,068 |
| Downloads all time | 17.4 M | 36.9 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2022-12-13 | 2022-12-12 |
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
12.7 M242 K
tf_efficientnetv2_s.in21k_ft_in1k
efficientnet_b3.ra2_in1k
A overtook B on 24 Sep
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
tf_efficientnetv2_s.in21k_ft_in1k · fp16
0.6 GB / 24 GB
efficientnet_b3.ra2_in1k · fp16
0.6 GB / 24 GB
Adjacent comparisons
vit-base-patch16-224 vs tf_efficientnetv2_s.in21k_ft_in1k
tf_efficientnetv2_s.in21k_ft_in1k vs Gender-Classifier-Mini
mobilenetv3_small_100.lamb_in1k vs tf_efficientnetv2_s.in21k_ft_in1k
resnet50.a1_in1k vs tf_efficientnetv2_s.in21k_ft_in1k
resnet18.a1_in1k vs tf_efficientnetv2_s.in21k_ft_in1k
tf_efficientnetv2_s.in21k_ft_in1k vs resnet34.a1_in1k