ProLLaMA
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
- How it was established
- Hardware
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
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
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.
ProLLaMA— who created it?
It was published by Peking University,Peng Cheng Laboratory, based in China, an organisation categorised as academia,Academia.
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.
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.
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.
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.
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.
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.