Llama 3 (8B/70B, about 15T tokens)
AIMade by AIWritten by AI (Claude) from the source below. Check anything important against the source.How it's made
Llama 3 (8B/70B, about 15T tokens)
Why it matters
The 8B delivered the previous generation's 70B-class performance, raising the bar for practical local use
Source — Primary sources first; secondary reports are labelled “Press”
Pressen.wikipedia.orghttps://en.wikipedia.org/wiki/Llama_(language_model)Added in Week 35, 2026 · See that week
On the map — ⑨ Open-Weight Lineage line
- Previous stopMistral Large
- This recordLlama 3
- Next stopEXAONE 3.0
In the model family tree — Llama family · 12 versions
- Earlier versionCode Llama
- This recordLlama 3
- Later versionLlama 3.1