BASIC-L
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
- Organisation type
- Industry
- Country
- United States of America
- Published
- 19 November 2021
- Authors
- Hieu Pham, Zihang Dai, Golnaz Ghiasi, Kenji Kawaguchi, Hanxiao Liu, Adams Wei Yu, Jiahui Yu, Yi-Ting Chen, Minh-Thang Luong, Yonghui Wu, Mingxing Tan, 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
- 8,905,031,712,000 tokens
2.4B image model + 670M text model
6.7B image-text pairs
Training compute
The arithmetic performed to train the model, measured in floating-point operations. It is a measure of what the training run cost, not of how fast the finished model answers you.
- Training compute
- 4.1 × 10²² FLOP
- How it was established
- Hardware
6.9k + 1k + 0.8k = 8.7k TPUv4 core-days for BASIC-L, per Table 8 Two cores per chip, and 275 teraflop/s per chip (https://cloud.google.com/tpu/docs/system-architecture-tpu-vm#tpu_v4) 275 teraflops * 8700/2 * 24 * 3600 * 0.4 (assumed utilization) = 8.3e22
The training run
What it physically took to train: which chips, how many, for how long, and what that drew from the wall.
- Training hardware
- Google TPU v4
- Chip-hours
- 4,350
- Compute cost
- $1,685
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
- Unreleased
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
- Likely
- Citations
- 241
SOTA on ImageNet for a model that was not trained on ImageNet images: "We present a combined scaling method – named BASIC – that achieves 85.7% top-1 accuracy on the ImageNet ILSVRC-2012 validation set without learning from any labeled ImageNet example. This accuracy surpasses best-published similar models – CLIP and ALIGN – by 9.3%"
Sources
Where this record came from and when it was last checked.
- Reference
- Combined Scaling for Zero-shot Transfer Learning
- Last updated
- 25 May 2026
What the numbers mean
Background
BASIC-L was published by Google, in United States of America, in November 2021. The organisation is categorised as industry.
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.
How it was trained
Producing it required around 4.1 × 10²² FLOP of arithmetic, on Google TPU v4, which is a statement about the training budget rather than about inference.
It was trained on about 8,905,031,712,000 tokens of text.
The reason it appears in this catalogue at all is sOTA improvement.
Answers
BASIC-L — common questions
What is BASIC-L used for?
BASIC-L works in Vision, and is recorded as handling image classification. These are the areas it was designed around; they describe intent rather than a hard boundary.
How much compute was used to train BASIC-L?
Around 4.1 × 10²² FLOP, on Google TPU v4. That measures what producing the model cost and says nothing about how quickly it answers once trained — inference speed comes from memory bandwidth, not from the training budget.
What GPU do I need to run BASIC-L?
None. BASIC-L 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 open source?
No. BASIC-L has not had its weights published, so it exists only as a service controlled by its owner.
How many parameters does BASIC-L have?
BASIC-L has 3.1B parameters. 2.4B image model + 670M text model. 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?
BASIC-L was published by Google, based in United States of America, categorised as industry.
When was BASIC-L released?
BASIC-L was published in November 2021. 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.