MooER

Closed weights Moore Threads 7.2B parameters August 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
Moore Threads
Organisation type
Industry
Country
China
Published
9 August 2024
Authors
Junhao Xu, Zhenlin Liang, Yi Liu, Yichao Hu, Jian Li, Yajun Zheng, Meng Cai, Hua Wang

What it does

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

Domain
Speech
Task
Speech recognition (ASR), Translation
Base model
Qwen2-7B

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
7.2B

7 B active parameters in the decoder (inherits Qwen-2-7B-instruct) + 158 M in the Paraformer audio encoder → ~ 7.2 B total.

Training data
tokens

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
MTT S4000
Chips used
8
Power draw
7.1 kW

How it is classified

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

Record confidence
Confident
Citations
3

Sources

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

Reference
MooER: LLM-based Speech Recognition and Translation Models from Moore Threads
Last updated
1 December 2025

What the numbers mean

About this model

MooER was published by Moore Threads, in the country recorded as China, during August 2024. It comes out of an organisation categorised as industry.

It works in the domain of Speech, and is recorded as performing the task of speech recognition (ASR), Translation.

Rather than being trained from scratch, it is derived from Qwen2-7B. Most models at this scale are adapted from an existing base rather than built from nothing.

Its weights were never published, so it can only be reached through its provider. No graphics card changes that.

Answers

MooER — common questions

01

MooER— what is it used for?

It works in the domain of Speech, and is recorded as handling the task of speech recognition (ASR), Translation. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

02

MooER— what GPU do I need to run it?

None. This 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

MooER— is it open source?

The licensing was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.

04

MooER— how many parameters does it have?

It has a parameter count of 7.2B. 7 B active parameters in the decoder (inherits Qwen-2-7B-instruct) + 158 M in the Paraformer audio encoder → ~ 7.2 B total. 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

MooER— who created it?

It was published by Moore Threads, based in China, an organisation categorised as industry.

06

MooER— when was it released?

It was published in August 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.

Source

Original publication

Record last updated 1 December 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.