Luca 2.0

Closed weights Mianbi Intelligence 100B parameters August 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
Mianbi Intelligence
Organisation type
Industry
Country
China
Published
29 August 2023

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
100B

https://www.leiphone.com/category/ai/23kbzQXj60xZgUgO.html English translation: "Li Dahai: From a technical point of view, the CPM2 (Chinese Pretrained Model) 100 billion model we launched at that time was a sparse model of MoE, which is different from the 100 billion model we are promoting now." This suggests it is a dense model.

Training data
tokens

"Assume Chinchilla-optimal dataset size" from training compute notes

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
1.2 × 10²⁴ FLOP

Assume Chinchilla-optimal dataset size: 20 * 100B * 100B * 6 = 1.2e24 FLOP

How it was established
Operation counting

The training run

What it physically took to train: which chips, how many, for how long, and what that drew from the wall.

Data centre
There is no paper to reference, no information about hardware used for training found in media.

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

could be accessible via API, though I have not found documentation here is accessible for chatting: https://luca.cn/home

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

Where it came from

Luca 2.0 was published by Mianbi Intelligence, in China, in August 2023. industry is the category the publisher falls under.

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

Training and provenance

Producing it required around 1.2 × 10²⁴ FLOP of arithmetic, which is a statement about the training budget rather than about inference.

Answers

Luca 2.0 — common questions

01

Who created Luca 2.0?

Luca 2.0 was published by Mianbi Intelligence, based in China, categorised as industry.

02

When was Luca 2.0 released?

Luca 2.0 was published in August 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.

03

How much compute was used to train Luca 2.0?

Around 1.2 × 10²⁴ FLOP. 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.

04

What GPU do I need to run Luca 2.0?

None. Luca 2.0 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.

05

Is Luca 2.0 open source?

No. Luca 2.0 has not had its weights published, so it exists only as a service controlled by its owner.

06

How many parameters does Luca 2.0 have?

Luca 2.0 has 100B parameters. https://www.leiphone.com/category/ai/23kbzQXj60xZgUgO.html English translation: "Li Dahai: From a technical point of view, the CPM2 (Chinese Pretrained Model) 100 billion model we launched at that time was a sparse model of MoE, which is different from the 100 billion model we are promoting now." This suggests it is a dense 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.

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.