FFN SwiGLU
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
- Organisation type
- Industry
- Country
- United States of America
- Published
- 14 February 2020
- Authors
- Noam Shazeer
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Language
- Task
- Language modeling, 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
- 220M
- Training data
- 50,600,083,456 tokens
"We use the same code base, model architecture, and training task as the base model from [Raffel et al.,2019]. The encoder and decoder each consist of 12 layers, with dmodel = 768. For the attention layers, h = 12 and dk = dv = 64. The FFN layers have hidden size df f = 3072." [Raffel et al.,2019]: "Specifically, both the encoder and decoder consist of 12 blocks (each block comprising self-attention, optional encoder-decoder attention, and a feed-forward network). The feed-forward networks in e…
pre-training: "Identically to [Raffel et al., 2019], we pre-train for 524,288 steps on the span-filling objective on the C4 dataset. Each training batch consists of 128 examples, each of which has an input of 512 tokens and an output of 114 tokens" 524288*128*(512+114) = 42010148864 fine-tuning: "Fine-tuning consists of 131072 steps <..>, the input sequences for each step have a combined length of approximately 65,536 tokens." 131072*65536 = 8589934592 42010148864+8589934592 = 50600083456
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
- 3.4 × 10¹⁹ FLOP
- How it was established
- Hardware,Operation counting
6 FLOP/parameter/token * 220000000 parameters * 50600083456 tokens = 66792110161920000000 FLOP (10^19) 45000000000000 FLOP/GPU/sec * 21.85 hours * 3600 sec / hour * 16 GPUs * 0.3 [assumed utilization] = 16990560000000002000 FLOP (10^19) sqrt(66792110161920000000*16990560000000002000) = 3.3687317e+19
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
- Google TPU v2
- Chips used
- 16
- Wall-clock time
- 22 hours
- Power draw
- 9.2 kW
"Each training step took approximately 0.15 seconds on a 32-core TPUv2 cluster" -> 16 chips "we pre-train for 524,288 steps" 524288*0.15/3600 ~ 21.85 hours
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
- Historical significance
- Record confidence
- Confident
the paper introduced SwiGLU
Sources
Where this record came from and when it was last checked.
- Reference
- GLU Variants Improve Transformer
- Last updated
- 28 November 2025
What the numbers mean
What this model is
FFN SwiGLU was published by Google, in United States of America, in February 2020. It comes out of industry.
It works in Language, and is recorded as doing language modeling, Question answering.
Its weights were never published, so it can only be reached through its provider. No graphics card changes that.
What went into building it
The training run consumed about 3.4 × 10¹⁹ FLOP, on Google TPU v2. That figure describes the cost of creating it and has no bearing on how quickly it generates text.
Around 50,600,083,456 tokens went into training it.
Its inclusion criterion is historical significance.
Answers
FFN SwiGLU — common questions
Is FFN SwiGLU open source?
No. FFN SwiGLU has not had its weights published, so it exists only as a service controlled by its owner.
How many parameters does FFN SwiGLU have?
FFN SwiGLU has 220M parameters. "We use the same code base, model architecture, and training task as the base model from [Raffel et al.,2019]. The encoder and decoder each consist of 12 layers, with dmodel = 768. For the attention layers, h = 12 and dk = dv = 64. The FFN layers have hidden size df f = 3072." [Raffel et al.,2019]: "Specifically, both the encoder and decoder consist of 12 blocks (each block comprising self-attention, optional encoder-decoder attention, and a feed-forward network). The feed-forward networks in each block consist of a dense layer with an output dimensionality of dff = 3072 followed by a ReLU nonlinearity and another dense layer. The “key” and “value” matrices of all attention mechanisms have an inner dimensionality of dkv = 64 and all attention mechanisms have 12 heads. All other sub-layers and embeddings have a dimensionality of dmodel = 768. In total, this results in a model with about 220 million parameters.". 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 FFN SwiGLU?
FFN SwiGLU was published by Google, based in United States of America, categorised as industry.
When was FFN SwiGLU released?
FFN SwiGLU was published in February 2020. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
What is FFN SwiGLU used for?
FFN SwiGLU works in Language, and is recorded as handling language modeling, Question answering. A model can carry several of each, so these are the areas it was built for rather than a limit on what it will attempt.
How much compute was used to train FFN SwiGLU?
Around 3.4 × 10¹⁹ FLOP, on Google TPU v2. 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 FFN SwiGLU?
None. FFN SwiGLU 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.
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.