ProteinChat

Closed weights University of California San Diego,BioMap Research,The Scripps Research Institute,Mohamed bin Zayed University of Artificial Intelligence (MBZUAI) 14B parameters October 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
University of California San Diego,BioMap Research,The Scripps Research Institute,Mohamed bin Zayed University of Artificial Intelligence (MBZUAI)
Organisation type
Academia,Industry,Academia
Country
United States of America, China, United Arab Emirates
Published
10 October 2024
Authors
Mingjia Huo, Han Guo, Xingyi Cheng, Digvijay Singh, Hamidreza Rahmani, Shen Li, Philipp Gerlof, Trey Ideker, Danielle A. Grotjahn, Elizabeth Villa, Le Song, Pengtao Xie

What it does

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

Domain
Biology
Task
Protein function prediction
Base model
xTrimoPGLM - 1B,Vicuna-13B v0

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
14B

"We utilized xTrimoPGLM (27), a state-of-the-art protein language model, as the protein encoder, and Vicuna- 13B (25), fine-tuned from Llama-2 (21), as the LLM of ProteinChat."

Training data
tokens

Assuming average protein length of 300 tokens (600 is the maximum length), 20 tokens for the prompt and 50 tokens for the answer. 1500000 examples * (300 tokens per protein + 70 prompt tokens) * 0.9 training split =499500000

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
Hardware

How it is classified

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

Record confidence
Likely
Citations
8

Sources

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

Reference
Multi-Modal Large Language Model Enables Protein Function Prediction
Last updated
1 January 2026

What the numbers mean

Background

ProteinChat was published by University of California San Diego,BioMap Research,The Scripps Research Institute,Mohamed bin Zayed University of Artificial Intelligence (MBZUAI), in United States of America, in October 2024. It comes out of academia,Industry,Academia.

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

Its starting point was xTrimoPGLM - 1B,Vicuna-13B v0 — most models at this scale are adapted from an existing base rather than built from nothing.

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

Answers

ProteinChat — common questions

01

What is ProteinChat used for?

ProteinChat 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.

02

What GPU do I need to run ProteinChat?

None. ProteinChat 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.

03

Is ProteinChat open source?

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

04

How many parameters does ProteinChat have?

ProteinChat has 14B parameters. "We utilized xTrimoPGLM (27), a state-of-the-art protein language model, as the protein encoder, and Vicuna- 13B (25), fine-tuned from Llama-2 (21), as the LLM of ProteinChat.". 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.

05

Who created ProteinChat?

ProteinChat was published by University of California San Diego,BioMap Research,The Scripps Research Institute,Mohamed bin Zayed University of Artificial Intelligence (MBZUAI), based in United States of America, categorised as academia,Industry,Academia.

06

When was ProteinChat released?

ProteinChat was published in October 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.

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.