SenseChat 5.0

Closed weights SenseTime 600B parameters April 2024

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
SenseTime
Organisation type
Industry
Country
Hong Kong
Published
23 April 2024
Authors
SenseNova Team

What it does

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

Domain
Language
Task
Chat, 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
600B

This article claims the model is a 600B MoE: https://www.sensetime.com/cn/news-detail/51168158?categoryId=72

Training data
1,835,000,000,000 tokens

Words per gygabyte for Mandarin Chinese: 167M 10000*167000000 = 1670000000000 "is trained based on more than 10TB of tokens, covers a large amount of synthetic data" However, a later news article from SenseTime itself said: "In terms of data, SenseChat V5 uses a new generation of data production pipelines to produce 10T tokens of high-quality training data." (It also says "10T tokens" in the original untranslated version).

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
Hosted access (no API)
Training code
Unreleased

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Likely above 10²³ FLOP
Yes
Record confidence
Likely

Sources

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

Last updated
28 November 2025

What the numbers mean

About this model

SenseChat 5.0 was published by SenseTime, in Hong Kong, in April 2024. The organisation is categorised as industry.

It works in Language, and is recorded as doing chat, Language modeling/generation.

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 was trained on about 1,835,000,000,000 tokens of text.

Answers

SenseChat 5.0 — common questions

01

When was SenseChat 5.0 released?

SenseChat 5.0 was published in April 2024. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

02

What is SenseChat 5.0 used for?

SenseChat 5.0 works in Language, and is recorded as handling chat, Language modeling/generation. These are the areas it was designed around; they describe intent rather than a hard boundary.

03

What GPU do I need to run SenseChat 5.0?

None. SenseChat 5.0 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.

04

Is SenseChat 5.0 open source?

No. SenseChat 5.0 has not had its weights published, so it exists only as a service controlled by its owner.

05

How many parameters does SenseChat 5.0 have?

SenseChat 5.0 has 600B parameters. This article claims the model is a 600B MoE: https://www.sensetime.com/cn/news-detail/51168158?categoryId=72. 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.

06

Who created SenseChat 5.0?

SenseChat 5.0 was published by SenseTime, based in Hong Kong, categorised as industry.

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.