LMSI-Palm

Closed weights Google,University of Illinois Urbana-Champaign (UIUC) 540B parameters October 2022

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 Illinois Urbana-Champaign (UIUC)
Organisation type
Industry,Academia
Country
United States of America
Published
20 October 2022
Authors
Jiaxin Huang, Shixiang Shane Gu, Le Hou, Yuexin Wu, Xuezhi Wang, Hongkun Yu, Jiawei Han

What it does

The problem areas the model was built for. A model can carry several of each.

Domain
Language
Task
Language generation, Language modeling/generation, Question answering, Mathematical reasoning
Base model
PaLM (540B)

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
540B

540B

Training data
1,920,000 tokens

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

Table 3 "We show that our approach improves the general reasoning ability of a 540B-parameter LLM (74.4%->82.1% on GSM8K, 78.2%->83.0% on DROP, 90.0%->94.4% on OpenBookQA, and 63.4%->67.9% on ANLI-A3) and achieves state-of-the-art-level performance, without any ground truth label."

Record confidence
Confident
Citations
851

Sources

Where this record came from and when it was last checked.

Reference
Large Language Models Can Self-Improve
Last updated
25 May 2026

What the numbers mean

Where it came from

LMSI-Palm was published by Google,University of Illinois Urbana-Champaign (UIUC), in United States of America, in October 2022. The organisation is categorised as industry,Academia.

It works in Language, and is recorded as doing language generation, Language modeling/generation, Question answering, Mathematical reasoning.

It builds on PaLM (540B), which is why it shares that model's general shape and size.

Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.

How it was trained

It was trained on about 1,920,000 tokens of text.

Its inclusion criterion is sOTA improvement.

Answers

LMSI-Palm — common questions

01

What is LMSI-Palm used for?

LMSI-Palm works in Language, and is recorded as handling language generation, Language modeling/generation, Question answering, Mathematical reasoning. These are the areas it was designed around; they describe intent rather than a hard boundary.

02

What GPU do I need to run LMSI-Palm?

None. LMSI-Palm 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.

03

Is LMSI-Palm open source?

No. LMSI-Palm has not had its weights published, so it exists only as a service controlled by its owner.

04

How many parameters does LMSI-Palm have?

LMSI-Palm has 540B parameters. 540B. 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.

05

Who created LMSI-Palm?

LMSI-Palm was published by Google,University of Illinois Urbana-Champaign (UIUC), based in United States of America, categorised as industry,Academia.

06

When was LMSI-Palm released?

LMSI-Palm was published in October 2022. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

Source

Original publication

Record last updated 25 May 2026

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.