Konan LLM 13B

Training compute

3.9×10²² FLOP

Parameters

13.1B

Published

Aug 15, 2023

Konan LLM 13B is an AI model developed by Konan Technology (South Korea), first published in August 2023. It works in the language and vision domain, on tasks such as language modeling/generation.

Training it took an estimated 3.9×10²² FLOP of compute (estimation method: operation counting). The model has 13,100,000,000 parameters. It was trained on roughly 492B datapoints.

Access: Hosted access (no API). Its weights are not openly released. Epoch AI rates the confidence of this record as likely.

Full record

Organization: Konan Technology
Country of organization: South Korea
Domain: Language, Vision
Task: Language modeling/generation
Training compute: 3.9×10²² FLOP
Compute estimation method: Operation counting
Parameters: 13,100,000,000
Dataset size: 492B
Model accessibility: Hosted access (no API)
Open weights: No
Epoch confidence: Likely