AI models
Falcon-H1
Training compute
3.7×10²⁴ FLOP
Parameters
34B
Published
May 21, 2025
Falcon-H1 is an AI model developed by Technology Innovation Institute (United Arab Emirates), first published in May 2025. It works in the language domain, on tasks such as language modeling/generation, question answering and code generation.
Training it took an estimated 3.7×10²⁴ FLOP of compute (estimation method: operation counting). The model has 34,000,000,000 parameters. It was trained on roughly 18T datapoints. Training ran on 4,096 NVIDIA H100 SXM5 80GB.
Access: Open weights (unrestricted). Its weights are openly available. Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- Technology Innovation Institute
- Country of organization
- United Arab Emirates
- Domain
- Language
- Task
- Language modeling/generation, Question answering, Code generation
- Training compute
- 3.7×10²⁴ FLOP
- Compute estimation method
- Operation counting
- Parameters
- 34,000,000,000
- Dataset size
- 18T
- Training hardware
- NVIDIA H100 SXM5 80GB
- Chips used
- 4,096
- Training power draw
- 5.6 MW
- Model accessibility
- Open weights (unrestricted)
- Open weights
- Yes
- Epoch confidence
- Confident
More from Technology Innovation Institute
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