M6-T
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
- 5 March 2021
- Authors
- An Yang, Junyang Lin, Rui Men, Chang Zhou, Le Jiang, Xianyan Jia, Ang Wang, Jie Zhang, Jiamang Wang, Yong Li, Di Zhang, Wei Lin, Lin Qu, Jingren Zhou, Hongxia Yang
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Multimodal, Language, Vision
- Task
- Chat, Image captioning
- Approach
- Self-supervised learning
- Numerical format
- FP16
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
- 1T
- Training data
- 111,800,000,000 tokens
Table 5. Note model is sparse MoE with 960 experts; not all parameters are activated on the forward pass.
60.5B images and 111.8B tokens of text
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
- 5.5 × 10²¹ FLOP
- How it was established
- Third-party estimation
Estimate taken from https://www.governance.ai/research-paper/recent-trends-chinas-llm-landscape
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 Tesla V100 DGXS 32 GB
- Chips used
- 480
- Power draw
- 243.3 kW
- Compute cost
- $13,157
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
- Training code
- 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
- SOTA improvement
- Record confidence
- Likely
- Citations
- 76
Improves on hardware SOTA for similar problems Abstract: "We push the model scale to over 1 trillion parameters and implement it on solely 480 NVIDIA V100-32GB GPUs, in comparison with the recent SOTAs [11; 6] on 2048 TPU cores."
Sources
Where this record came from and when it was last checked.
- Reference
- M6-T: Exploring Sparse Expert Models and Beyond
- Last updated
- 28 November 2025
What the numbers mean
What this model is
M6-T was published by Alibaba, in China, in March 2021. industry is the category the publisher falls under.
It works in Multimodal, Language, Vision, and is recorded as doing chat, Image captioning.
This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.
Training and provenance
Training it took roughly 5.5 × 10²¹ FLOP of computation, on NVIDIA Tesla V100 DGXS 32 GB — a measure of what producing the model cost, not of how fast it answers.
The training set ran to roughly 111,800,000,000 tokens.
The reason it appears in this catalogue at all is sOTA improvement.
Answers
M6-T — common questions
What is M6-T used for?
M6-T works in Multimodal, Language, Vision, and is recorded as handling chat, Image captioning. These are the areas it was designed around; they describe intent rather than a hard boundary.
How much compute was used to train M6-T?
Around 5.5 × 10²¹ FLOP, on NVIDIA Tesla V100 DGXS 32 GB. 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.
What GPU do I need to run M6-T?
None. M6-T 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.
Is M6-T open source?
No. M6-T has not had its weights published, so it exists only as a service controlled by its owner.
How many parameters does M6-T have?
M6-T has 1T parameters. Table 5. Note model is sparse MoE with 960 experts; not all parameters are activated on the forward pass. 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.
Who created M6-T?
M6-T was published by Alibaba, based in China, categorised as industry.
When was M6-T released?
M6-T was published in March 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.
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.