Protllm

Closed weights Beijing Institute of Technology,Beihang University,Peking University,Smart Grid Research Institute,Shanghai AI Lab February 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
Beijing Institute of Technology,Beihang University,Peking University,Smart Grid Research Institute,Shanghai AI Lab
Organisation type
Academia,Academia,Academia,Academia
Country
China
Published
28 February 2024
Authors
Le Zhuo, Zewen Chi, Minghao Xu, Heyan Huang, Heqi Zheng, Conghui He, Xian-Ling Mao, Wentao Zhang

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)
Base model
LLaMA-7B

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

Summary of calculations: PubMed Articles: 165,206 × 10,000 = 1.65206 × 10^9 UniProt Annotations: 64,634 × 100 = 6.4634 × 10^6 STRING Annotations: 25,682 × 100 = 2.5682 × 10^6 Mol-Instructions: 173,973 × 500 = 86.9865 × 10^6 Dataset total: 1.65206 × 10^9 + 6.4634 × 10^6 + 2.5682 × 10^6 + 86.9865 × 10^6 = 1.7475 × 10^9 Training tokens: 10,000 × 256 × 512 = 1.31072 × 10^9 Final estimate: 1.31 × 10^9 data points Training step based estimate: 10000 steps with batch size 256 and length 512 (Tabl…

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.

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 A100
Chips used
4
Power draw
3.2 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
Open (non-commercial)

no clear license for training and inference code https://github.com/ProtLLM/ProtLLM/tree/main weights are announced but not released https://huggingface.co/ProtLLM

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
29

Sources

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

Reference
ProtLLM: An Interleaved Protein-Language LLM with Protein-as-Word Pre-Training
Last updated
25 May 2026

What the numbers mean

Where it came from

Protllm was published by Beijing Institute of Technology,Beihang University,Peking University,Smart Grid Research Institute,Shanghai AI Lab, in China, in February 2024. It comes out of academia,Academia,Academia,Academia.

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

It builds on LLaMA-7B, which is why it shares that model's general shape and size.

Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.

Answers

Protllm — common questions

01

What GPU do I need to run Protllm?

None. Protllm 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 Protllm open source?

No. Protllm has not had its weights published, so it exists only as a service controlled by its owner.

03

How many parameters does Protllm have?

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

04

Who created Protllm?

Protllm was published by Beijing Institute of Technology,Beihang University,Peking University,Smart Grid Research Institute,Shanghai AI Lab, based in China, categorised as academia,Academia,Academia,Academia.

05

When was Protllm released?

Protllm was published in February 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 Protllm used for?

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

Source

Original publication

Record last updated 25 May 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.