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 3.1 8B
Released on Jul 23, 2024
The de-facto local workhorse: solid quality, 131K-token context and a huge GGUF quantization ecosystem. The standard choice for chat and assistants.
Features
- 8B params
- 131K context
- GGUF ecosystem
- Wide quant availability
Version history
- Llama 4 ScoutLatest
Prima generazione Llama nativamente multimodale e MoE, con 109B totali, 17B attivi e contesto da 10M token.
- Llama 3.2
Nuove taglie da 1B e 3B ottimizzate per l'edge, affiancate dai modelli vision da 11B e 90B.
- Llama 3.1 8B
Il contesto è passato da 8K a 128K token, con miglioramenti nel post-training e nel multilinguismo.
Tags
Useful links
Discover Llama 3.1 8B
Visit the official site to download, learn more and start using Llama 3.1 8B.
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 3.2 1B
Released Sep 25, 2024Llama 4 Scout
Small, fast model with up to 131K-token context. Ideal entry point for chat and summarization on modest hardware, great on phones and mini-PCs.
LLMLlamaLeggeroOpen Source