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 Maverick (MoE)
Released on Apr 5, 2025
Il modello MoE grande della famiglia Llama 4 di Meta: 400B di parametri totali con 17B attivi (128 esperti). Contesto 1M di token, nativamente multimodale (testo+immagini), licenza comunitaria Meta. Richiede multi-GPU o macchine con memoria unificata 128GB+ anche quantizzato.
Features
- 400B totali / 17B attivi
- MoE 128 esperti
- Contesto 1M
- Multimodale (testo+immagini)
- Licenza comunitaria Meta
Version history
- Llama 4 MaverickLatest
Seconda generazione Llama nativamente MoE e multimodale: 400B totali, 17B attivi, 128 esperti, contesto 1M, preaddestrato su ~22T token.
Tags
Useful links
Discover Llama 4 Maverick (MoE)
Visit the official site to download, learn more and start using Llama 4 Maverick (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