MoE-1.1T TPS calculator
Each card below is assessed against this model at the context length and minimum quality you choose. Speed is an estimate for a single request, calculated from the card's memory bandwidth and the size of the model once compressed.
Calculated for this model
818 cards we hold specifications for
Which GPUs can run MoE-1.1T?
Set the inputs, read the answer
A longer conversation needs more memory, which can push this model off smaller cards.
Hides cards that would only fit the model by compressing it below this point.
0 cards match
Calculating| Needs | Quantisation | Fit | |||||
|---|---|---|---|---|---|---|---|
|
No card in our catalogue can run this model with these settings. |
|||||||
Speeds are estimates for a single request — one conversation at a time — calculated from memory bandwidth, model size and quantisation. Real throughput varies with the inference runtime and its version. Figures published by hardware vendors measure many simultaneous requests and are much higher.
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
- Meta AI
- Organisation type
- Industry
- Country
- United States of America
- Published
- 20 December 2021
- Authors
- Mikel Artetxe, Shruti Bhosale, Naman Goyal, Todor Mihaylov, Myle Ott, Sam Shleifer, Xi Victoria Lin, Jingfei Du, Srinivasan Iyer, Ramakanth Pasunuru, Giri Anantharaman, Xian Li, Shuohui Chen, Halil Akin, Mandeep Baines, Louis Martin, Xing Zhou, Punit Singh Koura, Brian O'Horo, Jeff Wang, Luke Zettlemoyer, Mona Diab, Zornitsa Kozareva, Ves Stoyanov
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Language
- Task
- Language modeling/generation, Question answering
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
- 1.1T
- Training data
- 112,000,000,000 tokens
- Epochs
- 2.68
112B tokens, or 84B words at 0.75 English words/token. "We pretrain our models on a union of six Englishlanguage datasets, including the five datasets used to pretrain RoBERTa (Liu et al., 2019) and the English subset of CC100, totalling 112B tokens"
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
- 2.2 × 10²² FLOP
- How it was established
- Reported
Reported directly in paper. Authors calculate FLOPs analytically in appendix G
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
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 (non-commercial)
- Training code
- Unreleased
for research use only https://github.com/facebookresearch/fairseq/tree/main/examples/moe_lm I don't see training code
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
- 241
Sources
Where this record came from and when it was last checked.
- Reference
- Efficient Large Scale Language Modeling with Mixtures of Experts
- Last updated
- 25 May 2026
What the numbers mean
Hardware requirements in practice
MoE-1.1T reaches a parameter count of 1.1T. That is beyond what any single graphics card holds. Running it means either splitting it across several cards or renting hardware built for the job, and every card able to hold it alone is a datacentre part. The number that can: 0.
Where it came from
MoE-1.1T was published by Meta AI, in the country recorded as United States of America, during December 2021. The category the publisher falls under is industry.
It works in the domain of Language, and is recorded as performing the task of language modeling/generation, Question answering.
The weights are published, so it can be downloaded and run on your own hardware indefinitely, offline, with no account attached.
What went into building it
The training run consumed about 2.2 × 10²² FLOP, on hardware recorded as NVIDIA A100. That figure measures what producing the model cost, and has no bearing on how fast it answers.
It was trained on a corpus of about 112,000,000,000 tokens of text.
Step by step
How to choose a GPU for MoE-1.1T
The table above has already assessed every card we hold specifications for against this model. Getting to your answer takes six steps.
-
01
Start from the memory column
Every card here has been checked against MoE-1.1T. No amount of processing power compensates for a card that cannot hold it.
-
02
Decide how long your conversations run
Longer conversations cost memory on top of what the weights need. Move the slider to your real working length before trusting any row for MoE-1.1T.
-
03
Choose how far you will compress it
Each card runs the least-compressed copy it can hold. Setting a minimum quality drops the cards that only manage it by squeezing further than you would want, and holds the comparison at one level.
-
04
Compare tokens per second, not specifications
Sort by speed to see how cards rank for MoE-1.1T. It will not match a gaming ordering, because generation is bound by memory bandwidth.
-
05
Check the fit verdict before buying
Tight means it loads and works with no room to raise the context later, in the case of MoE-1.1T. Comfortable means you can grow the context later. That difference matters more than a few tokens per second, so buy for comfortable if you expect to.
-
06
Check the card from the other side
Each card page repeats this sweep for every model we hold, answering what else the hardware is good for beyond MoE-1.1T.
Answers
MoE-1.1T — common questions
MoE-1.1T— is it open source?
Its weights are published, so it 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.
MoE-1.1T— how many parameters does it have?
It has a parameter count of 1.1T. 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.
MoE-1.1T— who created it?
It was published by Meta AI, based in United States of America, an organisation categorised as industry.
MoE-1.1T— when was it released?
It was published in December 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.
MoE-1.1T— what is it used for?
It works in the domain of Language, and is recorded as handling the task of language modeling/generation, Question answering. These are the areas it was designed around; they describe intent rather than a hard boundary.
MoE-1.1T— where can I download it?
The weights are published, though we do not hold a repository link for it. This site calculates hardware requirements rather than hosting model files.
MoE-1.1T— how much compute was used to train it?
Training consumed around 2.2 × 10²² FLOP, on hardware recorded as NVIDIA A100. 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.
MoE-1.1T— can I run it if it does not fit in my GPU?
It can be split between the card and system memory, but it generates painfully slowly that way. The nearest miss we calculate falls short by 407.0 GB. Every figure here assumes the whole model is resident on the card.
MoE-1.1T— would two GPUs run it faster?
Two cards buy memory rather than speed, which matters only if one card cannot hold it. The number that can: 0. So a second card is rarely the answer here.
MoE-1.1T— why does the quantisation differ between cards?
Because capacity varies, so does how hard it has to be squeezed. The number of distinct levels in the table above: 1. Bigger cards get the more accurate version, and the quality floor above pins the comparison to one level.
MoE-1.1T— how accurate are these speed estimates?
They are calculated from specifications rather than measured, and each carries a range. One example: the range beneath each figure. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.
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.