Live
AI models

Yi-Lightning

Training compute
1.5×10²⁴ FLOP
Published
Oct 18, 2024

Yi-Lightning is an AI model developed by 01.AI (China), first published in October 2024. It works in the language domain, on tasks such as language modeling/generation.

Training it took an estimated 1.5×10²⁴ FLOP of compute (estimation method: hardware). Training ran on 2,000 NVIDIA H100 SXM5 80GB for about 720 hours.

Access: API access. Its weights are not openly released. Epoch AI rates the confidence of this record as confident.

Full record
Organization
01.AI
Country of organization
China
Domain
Language
Task
Language modeling/generation
Training compute
1.5×10²⁴ FLOP
Compute estimation method
Hardware
Training hardware
NVIDIA H100 SXM5 80GB
Chips used
2,000
Training time
720 h
Training power draw
2.8 MW
Model accessibility
API access
Open weights
No
Epoch confidence
Confident
Benchmark results
01Aider PolyglotPercent correct12.9
More from 01.AI
SourceEpoch AI, 'AI Models'. Published online at epoch.ai. Retrieved 2026-07-29 from https://epoch.ai/data/ai-models. Licensed under CC BY 4.0.
← All ai models