BASIC-L + Lion
No estimate
No hardware requirements for this model
The weights for this model have not been published, so it cannot be downloaded or run on your own hardware at any size. It is reachable only through its provider, and no graphics card changes that.
On record
Full specification
Everything on record for this model. Most of it describes how it was trained rather than how it runs — useful context for judging how much work went into it, and how it compares with models built at a different scale.
Origin
Who built this model, where, and when it was published.
- Organisation
- Google,University of California Los Angeles (UCLA)
- Organisation type
- Industry,Academia
- Country
- United States of America
- Published
- 13 February 2023
- Authors
- Xiangning Chen, Chen Liang, Da Huang, Esteban Real, Kaiyuan Wang, Yao Liu, Hieu Pham, Xuanyi Dong, Thang Luong, Cho-Jui Hsieh, Yifeng Lu, Quoc V. Le
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Vision
- Task
- Image classification
- Numerical format
- BF16
Size
How large the model is and how much data it was trained on. Parameters are the figure that decides whether it fits on a given graphics card.
- Parameters
- 3.1B
- Training data
- tokens
parameter count of original BASIC-L
The training run
What it physically took to train: which chips, how many, for how long, and what that drew from the wall.
- Chip-hours
- 4,350
Availability
Whether you can obtain the model and run it on your own hardware, which is what decides if any of the graphics-card figures on this page apply.
- Weights
- Closed — provider access only
- Model access
- Unreleased
- Training code
- Open source
Apache 2.0 https://github.com/google/automl/tree/master/lion
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Why it is tracked
- SOTA improvement
- Record confidence
- Confident
- Citations
- 626
"On vision-language contrastive learning, we achieve 88.3% zero-shot and 91.1% fine-tuning accuracy on ImageNet, surpassing the previous best results by 2% and 0.1%, respectively" "On image classification, Lion boosts the accuracy of ViT by up to 2% on ImageNet and saves up to 5x the pre-training compute on JFT."
Sources
Where this record came from and when it was last checked.
- Reference
- Symbolic Discovery of Optimization Algorithms
- Last updated
- 25 May 2026
What the numbers mean
Where it came from
BASIC-L + Lion was published by Google,University of California Los Angeles (UCLA), in United States of America, in February 2023. The organisation is categorised as industry,Academia.
It works in Vision, and is recorded as doing image classification.
Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.
Training and provenance
The reason it appears in this catalogue at all is sOTA improvement.
Answers
BASIC-L + Lion — common questions
What is BASIC-L + Lion used for?
BASIC-L + Lion works in Vision, and is recorded as handling image classification. A model can carry several of each, so these are the areas it was built for rather than a limit on what it will attempt.
What GPU do I need to run BASIC-L + Lion?
None. BASIC-L + Lion is a closed model — its weights were never published, so it cannot be downloaded or run on your own hardware at any price. It is reachable only through its provider.
Is BASIC-L + Lion open source?
No. BASIC-L + Lion has not had its weights published, so it exists only as a service controlled by its owner.
How many parameters does BASIC-L + Lion have?
BASIC-L + Lion has 3.1B parameters. parameter count of original BASIC-L. That figure is the total, and it is what decides how much memory the model needs — roughly half a gigabyte per billion at the compression most people use.
Who created BASIC-L + Lion?
BASIC-L + Lion was published by Google,University of California Los Angeles (UCLA), based in United States of America, categorised as industry,Academia.
When was BASIC-L + Lion released?
BASIC-L + Lion was published in February 2023. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
The other direction
Looking at it from the other side?
This page starts from the model. If you already own a card and want to know everything it will run, start from the hardware instead.