ERNIE-RNA

Closed weights Microsoft Research,Syngentech,Tsinghua University 86M parameters March 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
Microsoft Research,Syngentech,Tsinghua University
Organisation type
Industry,Industry,Academia
Country
United States of America, China
Published
17 March 2024
Authors
Weijie Yin, Zhaoyu Zhang, Liang He, Rui Jiang, Shuo Zhang, Gan Liu, Xuegong Zhang, Tao Qin, Zhen Xie

What it does

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

Domain
Biology
Task
Protein or nucleotide language model (pLM/nLM)

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
86M
Training data
918,000,000 tokens

Number of sequences (20.4M) × Maximum sequence length (1024) Average assumed length ~300 20.4M*300=6120000000

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
2.1 × 10²¹ FLOP

1. Hardware: 24x V100 32GB GPUs (1.30e+14 FLOPs/s per GPU) 2. Training duration: 20 days (directly provided) = 1.728e+6 seconds 3. Utilization: 40% 4. Calculation: 24 GPUs × 1.30e+14 FLOPs/s × 1.728e+6 seconds × 0.4 utilization = 2.1e+21 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 Tesla V100 DGXS 32 GB
Chips used
24
Wall-clock time
480 hours (20 days)
Power draw
11.9 kW

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
20

Sources

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

Reference
ERNIE-RNA: An RNA Language Model with Structure-enhanced Representations
Last updated
1 January 2026

What the numbers mean

What this model is

ERNIE-RNA was published by Microsoft Research,Syngentech,Tsinghua University, in United States of America, in March 2024. The organisation is categorised as industry,Industry,Academia.

It works in Biology, and is recorded as doing protein or nucleotide language model (pLM/nLM).

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 2.1 × 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 918,000,000 tokens.

Answers

ERNIE-RNA — common questions

01

What GPU do I need to run ERNIE-RNA?

None. ERNIE-RNA 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 ERNIE-RNA open source?

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

03

How many parameters does ERNIE-RNA have?

ERNIE-RNA has 86M 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.

04

Who created ERNIE-RNA?

ERNIE-RNA was published by Microsoft Research,Syngentech,Tsinghua University, based in United States of America, categorised as industry,Industry,Academia.

05

When was ERNIE-RNA released?

ERNIE-RNA was published in March 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.

06

What is ERNIE-RNA used for?

ERNIE-RNA works in Biology, and is recorded as handling protein or nucleotide language model (pLM/nLM). These are the areas it was designed around; they describe intent rather than a hard boundary.

07

How much compute was used to train ERNIE-RNA?

Around 2.1 × 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.

Source

Original publication

Record last updated 1 January 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.