AliceMind-MMU

Closed weights Alibaba November 2021

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
Alibaba
Organisation type
Industry
Country
China
Published
17 November 2021
Authors
Ming Yan, Haiyang Xu, Chenliang Li, Junfeng Tian, Bin Bi, Wei Wang, Weihua Chen, Xianzhe Xu, Fan Wang, Zheng Cao, Zhicheng Zhang, Qiyu Zhang, Ji Zhang, Songfang Huang, Fei Huang, Luo Si, Rong Jin

What it does

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

Task
Image Understanding
Approach
Supervised fine-tuning (SFT),Supervised

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.

Training data
12,649,000 tokens
Epochs
30

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
NVIDIA A100
Chips used
8
Power draw
6.5 kW

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

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
Historical significance,SOTA improvement

Was the top of the VQA Challenge Leaderboard for the standard test, scoring 81.26, surpassing both human and previous record-holder.

Record confidence
Likely

Sources

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

Reference
Achieving human parity on visual question answering
Last updated
30 June 2026

What the numbers mean

Where it came from

AliceMind-MMU was published by Alibaba, in China, in November 2021. industry is the category the publisher falls under.

and is recorded as doing image Understanding.

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

What went into building it

It was trained on about 12,649,000 tokens of text.

Its inclusion criterion is historical significance,SOTA improvement.

Answers

AliceMind-MMU — common questions

01

Is AliceMind-MMU open source?

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

02

How many parameters does AliceMind-MMU have?

No parameter count has been published for AliceMind-MMU, which is why no memory or speed figure appears on this page.

03

Who created AliceMind-MMU?

AliceMind-MMU was published by Alibaba, based in China, categorised as industry.

04

When was AliceMind-MMU released?

AliceMind-MMU was published in November 2021. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

05

What is AliceMind-MMU used for?

and is recorded as handling image Understanding. These are the areas it was designed around; they describe intent rather than a hard boundary.

06

What GPU do I need to run AliceMind-MMU?

None. AliceMind-MMU 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.

Source

Original publication

Record last updated 30 June 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.