Project AURIONAI Use-Cases Research & Innovation
UC Berkeley
vision

SqueezeNet

Small image classifier with AlexNet-level accuracy and 50 times fewer parameters (DeepScale and UC Berkeley).

UC BerkeleyUC BerkeleyUSA
Figure from the SqueezeNet paper: Microarchitectural view: Organization of convolution filters in the Fire module.
Levelmodel
Classvision
Parametersnot in the notes
Contextnot in the notes
Released24 Feb 2016
Opennessunknown
Runs onmobile or NPU
Statusactive

R&D Topics

Efficient vision networks for mobile and edge devicesproduced by

Identity

Developer
UC Berkeley
Family
not in the notes
Released
24 Feb 2016 sourcesannouncement page
Weights published
–
Record checked
12 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.

Architecture and Size

Architecture
CNN
Total parameters
– sources
Active parameters
–
Checkpoint parameters
–
Note
SqueezeNet 1.0 and 1.1.
Context length
not in the notes
Input
image
Output
labels and boxes
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).

Openness and Access

Openness
unknown
Licence
not in the notes sources
Access routes
open weights download, cloud marketplace
Where this comes from
The licence file governs over registry tags and aggregator labels.

Deployment

Runs on
mobile or NPU
Footprint
Edge or toolkit builds listed in: Qualcomm AI Hub.
Runtimes
not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.

Indonesia

Indonesian support
not stated
Regional languages
not in the notes
Jakarta hosting
unknown
Languages
not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.

Benchmark Results

The notes record no benchmark result for this model.

Lineage

The notes record no lineage for this model.

Industry Use Cases

No industry use case links this model.

Sources

  1. arxiv.org/abs/1602.07360 https://arxiv.org/abs/1602.07360
  2. jumpstart-cache-prod-us-west-2.s3.us-west-2.amazonaws.com/models_manifest.json https://jumpstart-cache-prod-us-west-2.s3.us-west-2.amazonaws.com/models_manifest.json
  3. aihub.qualcomm.com/models/squeezenet1_1 https://aihub.qualcomm.com/models/squeezenet1_1
  4. github.com/pytorch/vision/blob/main/torchvision/models/s... https://github.com/pytorch/vision/blob/main/torchvision/models/squeezenet.py
  5. pytorch.org/hub/pytorch_vision_squeezenet https://pytorch.org/hub/pytorch_vision_squeezenet
  6. raw.githubusercontent.com/pytorch/hub/master/pytorch_vision_squeezenet.md https://raw.githubusercontent.com/pytorch/hub/master/pytorch_vision_squeezenet.md
  7. modelzoo.co/model/squeezenet-caffe https://modelzoo.co/model/squeezenet-caffe
  8. arxiv.org/html/1602.07360 https://arxiv.org/html/1602.07360

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "SqueezeNet", https://aurion.semai.id/models/squeezenet/, records of October 2026.