ProLLaMA

Closed weights Peking University,Peng Cheng Laboratory 7B parameters 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
Peking University,Peng Cheng Laboratory
Organisation type
Academia,Academia
Country
China
Published
26 February 2024
Authors
Liuzhenghao Lv, Zongying Lin, Hao Li, Yuyang Liu, Jiaxi Cui, Calvin Yu-Chian Chen, Li Yuan, Yonghong Tian

What it does

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

Domain
Biology
Task
Protein question answering
Base model
Llama 2-7B

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.

Parameters
7B
Training data
tokens

52,807,283 sequences × 300 residues/sequence = 15,842,184,900 tokens ≈ 1.6 × 10^10 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
8.4 × 10²² FLOP

1. Hardware setup: 8x NVIDIA RTX A6000 GPUs (3.87e13 FLOP/s per GPU) 2. Training duration: Provided directly - Stage 1: 6 days, Stage 2: 5 days (Total: 11 days = 950,400 seconds) 3. Utilization rate: 40% 4. Calculation: (8 GPUs × 3.87e13 FLOP/s/GPU) × 950,400 seconds × 0.4 utilization = 1.2e20 FLOPs (Stage 1: 1.603e20 + Stage 2: 1.338e20) × 0.4 = 1.2e20 FLOPs Base model: 8.4e+22 total : 84120000000000000000000

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 RTX A6000
Chips used
8
Wall-clock time
264 hours (11 days)
Power draw
4.7 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
84

Sources

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

Reference
ProLLaMA: A Protein Language Model for Multi-Task Protein Language Processing
Last updated
25 May 2026

What the numbers mean

What this model is

ProLLaMA was published by Peking University,Peng Cheng Laboratory, in the country recorded as China, during February 2024. The category the publisher falls under is academia,Academia.

It works in the domain of Biology, and is recorded as performing the task of protein question answering.

It builds on Llama 2-7B. That is the usual way a specialised model is produced.

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

How it was trained

Training it took a computation budget of roughly 8.4 × 10²² FLOP, on hardware recorded as NVIDIA RTX A6000. That figure measures what producing the model cost, and has no bearing on how fast it answers.

Answers

ProLLaMA — common questions

01

ProLLaMA— how many parameters does it have?

It has a parameter count of 7B. 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.

02

ProLLaMA— who created it?

It was published by Peking University,Peng Cheng Laboratory, based in China, an organisation categorised as academia,Academia.

03

ProLLaMA— when was it released?

It 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.

04

ProLLaMA— what is it used for?

It works in the domain of Biology, and is recorded as handling the task of protein question answering. 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.

05

ProLLaMA— how much compute was used to train it?

Training consumed around 8.4 × 10²² FLOP, on hardware recorded as NVIDIA RTX A6000. 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.

06

ProLLaMA— what GPU do I need to run it?

None. This 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.

07

ProLLaMA— is it open source?

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

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.