Models🦙
Llama 3.1 405B
Released Jul 23, 2024Llama 4 Scout
Meta's largest open model: closed-frontier quality but datacenter requirements. In practice it needs high-VRAM multi-GPU or the cloud.
LLMLlamaFrontieraOpen Source
Back to resources
Llama 4 Scout (MoE)
Released on Apr 5, 2025
The compact MoE of the Llama 4 family: 17B active parameters out of 109B total (16 experts). Meta's community license allows free use under 700 million monthly users. One of the best entry points into the Llama 4 family.
Features
- 109B total / 17B active
- 16-expert MoE
- Multimodal (text+images)
- Meta community license
Version history
- Llama 4 ScoutLatest
Prima generazione Llama nativamente multimodale e MoE, con 109B totali, 17B attivi e contesto da 10M token.
Tags
Useful links
Discover Llama 4 Scout (MoE)
Visit the official site to download, learn more and start using Llama 4 Scout (MoE).
Related resources — Models
Models🦙
Llama 3.1 70B
Released Jul 23, 2024Llama 4 Scout
Frontier-class open model with 131K-token context. Needs 48-80GB VRAM, a Mac with unified memory, or a multi-GPU setup.
LLMLlamaFrontieraOpen Source
Models🦙
Llama 3.1 8B
Released Jul 23, 2024Llama 4 Scout
The de-facto local workhorse: solid quality, 131K-token context and a huge GGUF quantization ecosystem. The standard choice for chat and assistants.
LLMLlamaOpen SourceStandard