# Image Classification on ImageNet (val) (Accuracy, Size, and Memory)

Source: [Image Classification on ImageNet (val) (Accuracy, Size, and Memory)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-val-accuracy-size-and-memory>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T05:52:55.913Z

Evaluation of Image Classification performance on the validation split of the ImageNet dataset, reporting accuracy alongside model size and inference memory consumption.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Image Classification |
| Dataset (including any stated split) | ImageNet (val) |
| Metric | Model Size (Mbits) |
| Unit | SIZE |
| Direction | Lower is better |
| Results loaded | 4 of 4 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Model Size (Mbits)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-val-accuracy-size-and-memory.md?metric=Model%20Size%20(Mbits)>): Lower is better; unit: SIZE.

- [Top-5 Acc](<https://www.sota2.com/research/sota/image-classification-on-imagenet-val-accuracy-size-and-memory.md?metric=Top-5%20Acc>): Higher is better; unit: PERCENT.

- [Inference Memory (Feature Maps) (Mbits)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-val-accuracy-size-and-memory.md?metric=Inference%20Memory%20(Feature%20Maps)%20(Mbits)>): Lower is better; unit: SIZE.

## Recorded results

| Method | Model Size (Mbits) | Result date | Report paper |
| --- | --- | --- | --- |
| IFQ-AlexNet | 58.8 | Not recorded | 68fa66ab1e209131cea118e6 |
| IFQ-AlexNet | 58.8 | Not recorded | 68fa66ab1e209131cea118e6 |
| Lin et al. | 127.3 | Not recorded | 68fa66ab1e209131cea118e6 |
| Lin et al. | 128.5 | Not recorded | 68fa66ab1e209131cea118e6 |

### IFQ-AlexNet

Model Size (Mbits): 58.8. Result ID: 698cffa68b517eb4331e4473.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66ab1e209131cea118e6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66ab1e209131cea118e6.md>)

Recorded evaluation configuration: {"k":"2"}. This record does not assert independent reproduction.

### IFQ-AlexNet

Model Size (Mbits): 58.8. Result ID: 698cffa68b517eb4331e4474.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66ab1e209131cea118e6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66ab1e209131cea118e6.md>)

Recorded evaluation configuration: {"k":"4"}. This record does not assert independent reproduction.

### Lin et al.

Model Size (Mbits): 127.3. Result ID: 698cffa68b517eb4331e4471.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66ab1e209131cea118e6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62851e209131ce9f9d6e.md>)

Recorded evaluation configuration: {"gamma":"9"}. This record does not assert independent reproduction.

### Lin et al.

Model Size (Mbits): 128.5. Result ID: 698cffa68b517eb4331e4472.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66ab1e209131cea118e6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62851e209131ce9f9d6e.md>)

Recorded evaluation configuration: {"gamma":"10"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.