Falcon H1R 7B
Falcon H1R 7B is a reasoning model from the Technology Innovation Institute, released on January 5, 2026, built on Falcon-H1-7B-Base with a hybrid Transformer and Mamba2 architecture and trained with long reasoning traces and reinforcement learning for mathematics, programming, instruction following and logic.
Released
January 5, 2026
Type
reasoning
License
open-weight
Falcon-LLM License
Context
—
Capabilities
textreasoningcode
Architecture
Parameters: 7B
Sources
Every figure on this page was checked against these pages on . A figure we could not source is left out.
- TII press release: Falcon H1R 7B (opens in a new tab)
- Falcon LLM: Falcon H1R 7B (opens in a new tab)
- Hugging Face: tiiuae/Falcon-H1R-7B (opens in a new tab)
- Falcon blog: Falcon H1R 7B (opens in a new tab)
- Technical report (arXiv 2601.02346) (opens in a new tab)
Spotted something out of date? Tell us.