FMMformer (2-kernel fast weight + Band20)

Closed weights University of California Los Angeles (UCLA),University of Utah 40M parameters August 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
University of California Los Angeles (UCLA),University of Utah
Organisation type
Academia,Academia
Country
United States of America
Published
5 August 2021
Authors
Tan M. Nguyen, Vai Suliafu, Stanley J. Osher, Long Chen, Bao Wang

What it does

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

Domain
Language
Task
Language modeling, Text classification

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
40M

40M (caption to Table 2)

Training data
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
2.5 × 10¹⁶ FLOP

6 FLOP / token / parameter * 40 * 10^6 parameters * 103*10^6 tokens * 1 epoch [assumed, not given] = 2.472e+16 FLOP ________ estimation from the Algorithmic progress paper: 4.3*10^17 FLOP

How it was established
Operation counting

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 GeForce RTX 3090 Ti
Chips used
4
Power draw
3.6 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
Training code
Unreleased

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Record confidence
Speculative
Citations
38
Benchmark data
FMMformer (2-kernel fast weight + Band20)

Sources

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

Reference
FMMformer: Efficient and Flexible Transformer via Decomposed Near-field and Far-field Attention
Last updated
11 February 2026

What the numbers mean

Where it came from

FMMformer (2-kernel fast weight + Band20) was published by University of California Los Angeles (UCLA),University of Utah, in United States of America, in August 2021. It comes out of academia,Academia.

It works in Language, and is recorded as doing language modeling, Text classification.

This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.

What went into building it

Training it took roughly 2.5 × 10¹⁶ FLOP of computation, on NVIDIA GeForce RTX 3090 Ti — a measure of what producing the model cost, not of how fast it answers.

Answers

FMMformer (2-kernel fast weight + Band20) — common questions

01

What GPU do I need to run FMMformer (2-kernel fast weight + Band20)?

None. FMMformer (2-kernel fast weight + Band20) 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.

02

Is FMMformer (2-kernel fast weight + Band20) open source?

No. FMMformer (2-kernel fast weight + Band20) has not had its weights published, so it exists only as a service controlled by its owner.

03

How many parameters does FMMformer (2-kernel fast weight + Band20) have?

FMMformer (2-kernel fast weight + Band20) has 40M parameters. 40M (caption to Table 2). 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.

04

Who created FMMformer (2-kernel fast weight + Band20)?

FMMformer (2-kernel fast weight + Band20) was published by University of California Los Angeles (UCLA),University of Utah, based in United States of America, categorised as academia,Academia.

05

When was FMMformer (2-kernel fast weight + Band20) released?

FMMformer (2-kernel fast weight + Band20) was published in August 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.

06

What is FMMformer (2-kernel fast weight + Band20) used for?

FMMformer (2-kernel fast weight + Band20) works in Language, and is recorded as handling language modeling, Text classification. 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.

07

How much compute was used to train FMMformer (2-kernel fast weight + Band20)?

Around 2.5 × 10¹⁶ FLOP, on NVIDIA GeForce RTX 3090 Ti. 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.

Source

Original publication

Record last updated 11 February 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.