PPLX-70B-Online

Closed weights Perplexity 70B parameters November 2023

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
Perplexity
Organisation type
Industry
Country
United States of America
Published
29 November 2023
Authors
Lauren Yang, Kevin Hu, Aarash Heydari, Gradey Wang, Dmitry Pervukhin, Nikhil Thota, Alexandr Yarats, Max Morozov, Denis Yarats

What it does

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

Domain
Language
Task
Question answering, Chat, Language modeling/generation
Base model
Llama 2-70B

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
70B

70B

Training data
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
API access
Training code
Unreleased

https://docs.perplexity.ai/home

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
Significant use

Probably significant use: "Perplexity, which has just 41 employees and is based out of a shared working space in San Francisco, has 10 million monthly active users, an impressive number for a young start-up." However, this includes everyone who uses Perplexity's app which also uses third party models like GPT-4. https://www.nytimes.com/2024/02/01/technology/perplexity-search-ai-google.html

Record confidence
Likely

Sources

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

Reference
Introducing PPLX Online LLMs
Last updated
28 November 2025

What the numbers mean

Background

PPLX-70B-Online was published by Perplexity, in United States of America, in November 2023. The organisation is categorised as industry.

It works in Language, and is recorded as doing question answering, Chat, Language modeling/generation.

It is derived from Llama 2-70B rather than trained from scratch, which is the usual way a specialised model is produced.

This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.

How it was trained

It is tracked in the underlying dataset for one reason in particular: significant use.

Answers

PPLX-70B-Online — common questions

01

What GPU do I need to run PPLX-70B-Online?

None. PPLX-70B-Online 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.

02

Is PPLX-70B-Online open source?

No. PPLX-70B-Online has not had its weights published, so it exists only as a service controlled by its owner.

03

How many parameters does PPLX-70B-Online have?

PPLX-70B-Online has 70B parameters. 70B. 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.

04

Who created PPLX-70B-Online?

PPLX-70B-Online was published by Perplexity, based in United States of America, categorised as industry.

05

When was PPLX-70B-Online released?

PPLX-70B-Online was published in November 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.

06

What is PPLX-70B-Online used for?

PPLX-70B-Online works in Language, and is recorded as handling question answering, Chat, Language modeling/generation. These are the areas it was designed around; they describe intent rather than a hard boundary.

Source

Original publication

Record last updated 28 November 2025

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.