AltCLIP_M9

Open weights Beijing Academy of Artificial Intelligence / BAAI November 2022

No estimate

No hardware requirements for this model

This model's weights are open, but no parameter count has been published for it. Every memory and speed figure starts from that number, so we would rather show nothing than a fabricated estimate.

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
Beijing Academy of Artificial Intelligence / BAAI
Organisation type
Academia
Country
China
Published
12 November 2022
Authors
Zhongzhi Chen, Guang Liu, Bo-Wen Zhang, Fulong Ye, Qinghong Yang, Ledell Wu

What it does

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

Domain
Multimodal, Language, Vision
Task
Language modeling/generation, Chat, Visual question answering, Image generation
Base model
CLIP (ViT L/14@336px)
Numerical format
FP32

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
tokens
Epochs
10

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
Open — downloadable
Model access
Open weights (unrestricted)
Training code
Open source

https://github.com/FlagAI-Open/FlagAI/blob/master/examples/AltCLIP/altclip_ft_bmtrain.py Apache-2.0 license

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
SOTA improvement

"We set new state-of-the-art performances on a bunch of tasks including ImageNet-CN, Flicker30kCN, COCO-CN and XTD"

Record confidence
Unknown
Citations
113

Sources

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

Reference
AltCLIP: Altering the Language Encoder in CLIP for Extended Language Capabilities
Last updated
25 May 2026

What the numbers mean

What this model is

AltCLIP_M9 was published by Beijing Academy of Artificial Intelligence / BAAI, in China, in November 2022. It comes out of academia.

It works in Multimodal, Language, Vision, and is recorded as doing language modeling/generation, Chat, Visual question answering, Image generation.

It is derived from CLIP (ViT L/14@336px) rather than trained from scratch, which is the usual way a specialised model is produced.

The weights are published, so it can be downloaded and run on your own hardware indefinitely, offline, with no account attached.

Training and provenance

Its inclusion criterion is sOTA improvement.

Answers

AltCLIP_M9 — common questions

01

Who created AltCLIP_M9?

AltCLIP_M9 was published by Beijing Academy of Artificial Intelligence / BAAI, based in China, categorised as academia.

02

When was AltCLIP_M9 released?

AltCLIP_M9 was published in November 2022. 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

What is AltCLIP_M9 used for?

AltCLIP_M9 works in Multimodal, Language, Vision, and is recorded as handling language modeling/generation, Chat, Visual question answering, Image generation. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

04

Where can I download AltCLIP_M9?

The weights for AltCLIP_M9 are published, though we do not hold a repository link for it. This site calculates hardware requirements rather than hosting model files.

05

What GPU do I need to run AltCLIP_M9?

We cannot say. AltCLIP_M9 has open weights, but no parameter count has been published for it, and every memory and speed calculation starts from that number. We would rather show nothing than a fabricated estimate.

06

Is AltCLIP_M9 open source?

Its weights are published, so AltCLIP_M9 can be downloaded and run on your own hardware. Note that open weights is not the same as open source in the full sense — it says nothing about the training data, the training code, or the commercial terms attached.

07

How many parameters does AltCLIP_M9 have?

No parameter count has been published for AltCLIP_M9, which is why no memory or speed figure appears on this page.

Source

Original publication

Record last updated 25 May 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.