TAWFN

Closed weights Northeastern University (China) September 2024

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
Northeastern University (China)
Organisation type
Academia
Country
China
Published
23 September 2024
Authors
Lu Meng, Xiaoran Wang

What it does

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

Domain
Biology
Task
Protein function prediction

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

PDBset Training = 36,629 * 0.8 = 29,303 AFset Training = 42,427 Total = 29,303 + 42,427 = 71,730

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
3.5 × 10¹⁸ FLOP

1. Hardware setup: 1x NVIDIA GeForce RTX 3090 (1.60 x 10^14 FLOPs/s per GPU) 2. Training duration: Estimated * 71,000 samples, batch size 64 → 1,100 batches/epoch * 0.5s/batch → 9 min/epoch * 100 epochs → 15 hours (54,000 seconds) 3. Utilization rate: 40% 4. Final calculation: 1.60 x 10^14 FLOPs/s × 1 GPU × 54,000s × 0.4 = 3.456 x 10^18 FLOPs

How it was established
Hardware

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
Chips used
1
Power draw
379 W

How it is classified

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

Record confidence
Confident

Sources

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

Reference
TAWFN: A Deep Learning Framework for Protein Function Prediction
Last updated
28 November 2025

What the numbers mean

Background

TAWFN was published by Northeastern University (China), in China, in September 2024. academia is the category the publisher falls under.

It works in Biology, and is recorded as doing protein function prediction.

Its weights were never published, so it can only be reached through its provider. No graphics card changes that.

Training and provenance

Training it took roughly 3.5 × 10¹⁸ FLOP of computation, on NVIDIA GeForce RTX 3090 — a measure of what producing the model cost, not of how fast it answers.

Answers

TAWFN — common questions

01

Who created TAWFN?

TAWFN was published by Northeastern University (China), based in China, categorised as academia.

02

When was TAWFN released?

TAWFN was published in September 2024. 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 TAWFN used for?

TAWFN works in Biology, and is recorded as handling protein function prediction. These are the areas it was designed around; they describe intent rather than a hard boundary.

04

How much compute was used to train TAWFN?

Around 3.5 × 10¹⁸ FLOP, on NVIDIA GeForce RTX 3090. 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.

05

What GPU do I need to run TAWFN?

None. TAWFN 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.

06

Is TAWFN open source?

The licensing for TAWFN was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.

07

How many parameters does TAWFN have?

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

Source

Original publication

Record last updated 28 November 2025

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.