# Llama 2 70B
**Entity class:** Language model
**As of:** November 17, 2026
## Definition
**Llama 2 70B** is the Llama model used in later published work on Petals-based internet inference. This node belongs to the **distributed inference** route of [[wiki/Distributed Compute Ecosystem|Distributed Compute Ecosystem]], which records the specific kind of work or network capacity involved.
## Relationships
- **served by:** [[wiki/Petals|Petals]].
- **mechanism route:** [[wiki/Distributed Compute Ecosystem|Distributed Compute Ecosystem]].
- **source article:** [[articles/Embedded Super-Spreader Events and Muse|Embedded Super-Spreader Events and Muse]].
## Sources
- [Llama 2 70B — project record or attributed account](https://arxiv.org/abs/2312.08361).