PaLM 2
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
- 10 May 2023
- Authors
- Andrew M. Dai, David R. So, Dmitry Lepikhin, Jonathan H. Clark, Maxim Krikun, Melvin Johnson, Nan Du, Rohan Anil, Siamak Shakeri, Xavier Garcia, Yanping Huang, Yi Tay, Yong Cheng, Yonghui Wu, Yuanzhong Xu, Yujing Zhang, Zachary Nado, Bryan Richter, Alex Polozov, Andrew Nystrom, Fangxiaoyu Feng, Hanzhao Lin, Jacob Austin, Jacob Devlin, Kefan Xiao, Orhan Firat, Parker Riley, Steven Zheng, Yuhuai Wu,…
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Language
- Task
- Language modeling, Language modeling/generation
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
- 340B
- Training data
- 3,600,000,000,000 tokens
Model Architecture: "PaLM-2 is a new state-of-the-art language model. We have small, medium, and large variants that use stacked layers based on the Transformer architecture, with varying parameters depending on model size. Further details of model size and architecture are withheld from external publication." However, the parameter count was leaked to CNBC: https://www.cnbc.com/2023/05/16/googles-palm-2-uses-nearly-five-times-more-text-data-than-predecessor.html
"The pre-training corpus is significantly larger than the corpus used to train PaLM" so greater than 6e+11. According to the leaked documents viewed by CNBC, the corpus was 3.6 trillion tokens or around 2.7*10^12 words. https://www.cnbc.com/2023/05/16/googles-palm-2-uses-nearly-five-times-more-text-data-than-predecessor.html
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
- 7.3 × 10²⁴ FLOP
- How it was established
- Operation counting
Compute Requirements "Not reported." Paper suggests heuristic of C=6ND. Based on 340B parameters and 3.6T tokens, training compute would be around 7.3*10^24 FLOP.
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
- Compute cost
- $5,014,267
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
- API access
- Training code
- Unreleased
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Frontier model
- Yes
- Foundation model
- Yes
- Likely above 10²³ FLOP
- Yes
- Why it is tracked
- SOTA improvement,Training cost,Significant use,Highly cited
- Record confidence
- Likely
- Citations
- 1,734
Significant use: Gmail and Google Docs have millions of users. SOTA performance: Table 5 "At I/O today, we announced over 25 new products and features powered by PaLM 2. That means that PaLM 2 is bringing the latest in advanced AI capabilities directly into our products and to people — including consumers, developers, and enterprises of all sizes around the world. Here are some examples: PaLM 2’s improved multilingual capabilities are allowing us to expand Bard to new languages, starting today. …
Sources
Where this record came from and when it was last checked.
- Reference
- PaLM 2 Technical Report
- Last updated
- 18 December 2025
What the numbers mean
What this model is
PaLM 2 was published by Google, in United States of America, in May 2023. The organisation is categorised as industry.
It works in Language, and is recorded as doing language modeling, Language modeling/generation.
Its weights were never published, so it can only be reached through its provider. No graphics card changes that.
How it was trained
The training run consumed about 7.3 × 10²⁴ FLOP, on Google TPU v4. That figure describes the cost of creating it and has no bearing on how quickly it generates text.
The training set ran to roughly 3,600,000,000,000 tokens.
It is tracked in the underlying dataset for one reason in particular: sOTA improvement,Training cost,Significant use,Highly cited.
Answers
PaLM 2 — common questions
Who created PaLM 2?
PaLM 2 was published by Google, based in United States of America, categorised as industry.
When was PaLM 2 released?
PaLM 2 was published in May 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.
What is PaLM 2 used for?
PaLM 2 works in Language, and is recorded as handling language modeling, Language modeling/generation. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.
How much compute was used to train PaLM 2?
Around 7.3 × 10²⁴ 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 PaLM 2?
None. PaLM 2 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 PaLM 2 open source?
No. PaLM 2 has not had its weights published, so it exists only as a service controlled by its owner.
How many parameters does PaLM 2 have?
PaLM 2 has 340B parameters. Model Architecture: "PaLM-2 is a new state-of-the-art language model. We have small, medium, and large variants that use stacked layers based on the Transformer architecture, with varying parameters depending on model size. Further details of model size and architecture are withheld from external publication." However, the parameter count was leaked to CNBC: https://www.cnbc.com/2023/05/16/googles-palm-2-uses-nearly-five-times-more-text-data-than-predecessor.html. 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.
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.