Konan LLM 13B
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
- Konan Technology
- Organisation type
- Industry
- Country
- Korea (Republic of)
- Published
- 15 August 2023
- Authors
- Yang Seung-hyun, Wiretin, Changmin, Kim Jong-tae
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Language, Vision
- Task
- Language modeling/generation
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
- 13.1B
- Training data
- 492,000,000,000 tokens
'Konan LLM' has 13.1 billion parameters.
"492 billion total tokens" from https://techfinch.kr/ai/konan-technology-unveils-konan-llm--its-own-ai-language-model Since 2007, via the real-time AI analysis service pulseK, over 20.5 billion pieces of data have been independently secured. Among them, only 2 billion high-quality, large-scale data pieces have been used for training.
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
- 3.9 × 10²² FLOP
- How it was established
- Operation counting
=13100000000 parameters * 492000000000 tokens [see dataset size notes] * 6 FLOP / token / parameter =3.86712 × 10^22 FLOP
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
- Hosted access (no API)
- Training code
- Unreleased
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Record confidence
- Likely
Sources
Where this record came from and when it was last checked.
- Reference
- Konan LLM: A Korean Large Language Model
- Last updated
- 28 November 2025
What the numbers mean
About this model
Konan LLM 13B was published by Konan Technology, in Korea (Republic of), in August 2023. It comes out of industry.
It works in Language, Vision, and is recorded as doing language modeling/generation.
Its weights were never published, so it can only be reached through its provider. No graphics card changes that.
What went into building it
Training it took roughly 3.9 × 10²² FLOP of computation — a measure of what producing the model cost, not of how fast it answers.
It was trained on about 492,000,000,000 tokens of text.
Answers
Konan LLM 13B — common questions
How many parameters does Konan LLM 13B have?
Konan LLM 13B has 13.1B parameters. 'Konan LLM' has 13.1 billion 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.
Who created Konan LLM 13B?
Konan LLM 13B was published by Konan Technology, based in Korea (Republic of), categorised as industry.
When was Konan LLM 13B released?
Konan LLM 13B was published in August 2023. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
What is Konan LLM 13B used for?
Konan LLM 13B works in Language, Vision, and is recorded as handling language modeling/generation. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.
How much compute was used to train Konan LLM 13B?
Around 3.9 × 10²² FLOP. 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.
What GPU do I need to run Konan LLM 13B?
None. Konan LLM 13B 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.
Is Konan LLM 13B open source?
No. Konan LLM 13B has not had its weights published, so it exists only as a service controlled by its owner.
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.