SAVRN Model Hub · Comparisons
efficientnet_b3.ra2_in1k vs resnet18.a1_in1k
Efficientnet_b3.ra2_in1k has 12M parameters and resnet18.a1_in1k has 12M parameters; both are released under Apache License 2.0; at 16-bit, efficientnet_b3.ra2_in1k needs about 0 GB (1x MI300X from $1.85 an hour) and resnet18.a1_in1k about 0 GB (1x MI300X from $1.85 an hour).
| Field | efficientnet_b3.ra2_in1k timm/efficientnet_b3.ra2_in1k | resnet18.a1_in1k timm/resnet18.a1_in1k |
|---|---|---|
| Publisher | PyTorch Image Models | PyTorch Image Models |
| Task | Image classification | Image classification |
| Modality | Image | Image |
| Parameters, as reported | 12M parameters | 12M parameters |
| Architecture | Not stated | Not stated |
| Library | timm | timm |
| Context length | Not stated | Not stated |
| Repository size | 98.8 MB | 93.7 MB |
| Artifact formats | safetensors, pytorch | safetensors, pytorch |
| License | apache-2.0 | apache-2.0 |
| Access | Open weights, no gate | Open weights, no gate |
| Memory at 16-bit (weights and margin) | 0 GB | 0 GB |
| Cheapest GPUs at 16-bit, per hour | 1x MI300X, $1.85 | 1x MI300X, $1.85 |
| Memory at 4-bit (weights and margin) | 0 GB | 0 GB |
| Cheapest GPUs at 4-bit, per hour | 1x MI300X, $1.85 | 1x MI300X, $1.85 |
| Revision viewed | 0366a7551862 | 491b427b45c9 |
| Downloads reported by the hub | 1M | 2.2M |
| Last observed | 2026-10-02 | 2026-10-09 |
An evaluation row appears only where at least two of these models report the same benchmark with the same stated configuration, metric, unit and setup. Different evaluators stay named in each cell. Values are shown as reported: no unit conversion, no ranking.
SAVRN's Notes on efficientnet_b3.ra2_in1k
Twelve million parameters trained with the RandAugment RA2 recipe on ImageNet-1k, and the whole thing rounds to 0.0 GB at every precision on our table against a 192 GB MI300X at $1.85 an hour. Nobody rents a datacenter GPU for this; the honest deployment target is CPU or the smallest edge accelerator you own, and quantization is pointless at this size. This is a timm 'B' recipe, evolved from the ResNet Strikes Back line, so read it as a reference implementation rather than a frontier result.
Apache 2.0 permits commercial use and redistribution with the standard notice and patent terms. Treat it as a baseline: the same timm family lists ConvNeXtV2, DenseNet-121 and RepVGG neighbors that beat it on accuracy-per-dollar for many tasks, so benchmark before defaulting to EfficientNet out of habit. It draws 1.1M downloads a month and stays popular mostly as a cheap pretraining starting point and a stable comparison target.
SAVRN's Notes on resnet18.a1_in1k
12M parameters, 93.6 MB of weights, and memory lines that round to 0.0 GB at every precision — resnet18.a1_in1k is a CPU model that the Runs On table lists against a 192 GB MI300X at $1.85 an hour only for completeness. It draws 2M downloads a month as an ImageNet-1k reference checkpoint, and the page ties it to arXiv:1512.03385 and arXiv:2110.00476.
Apache 2.0 permits commercial use with notices kept. Treat it as a baseline rather than a recommendation: it deploys anywhere and trains cheaply, but newer timm recipes at similar latency beat the 2015 architecture on accuracy. Use it to sanity-check data pipelines and as the small end of an accuracy-versus-cost bracket against larger classifiers in this directory; step up within timm when accuracy starts to pay.
Questions
Which is larger, efficientnet_b3.ra2_in1k or resnet18.a1_in1k?
efficientnet_b3.ra2_in1k (12M parameters) is larger than resnet18.a1_in1k (12M parameters), by the parameter counts their publishers report.
Which is cheaper to run, efficientnet_b3.ra2_in1k or resnet18.a1_in1k?
At 4-bit, efficientnet_b3.ra2_in1k fits on 1x MI300X from $1.85 an hour and resnet18.a1_in1k on 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.
Can I use efficientnet_b3.ra2_in1k commercially?
Yes. efficientnet_b3.ra2_in1k is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.
Can I use resnet18.a1_in1k commercially?
Yes. resnet18.a1_in1k is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.