metaai·lightalo unofficial · independent
Universe / Language & LLMs / Llama 3 / 3.1 / 3.2 / 3.3
Language & LLMs · 2024

Llama 3 / 3.1 / 3.2 / 3.3

405B: the first GPT-4-class model anyone could download

open source superseded 1B / 3B / 8B / 11B / 70B / 90B / 405B params

Latest: Llama 3.3 70B (Dec 2024)

The 2024 herd: Llama 3 8B/70B (Apr 2024), Llama 3.1 with the 405B milestone (Jul 2024) — the first open frontier-class model — Llama 3.2 edge sizes (1B/3B) plus 11B/90B vision models (Sep 2024), and Llama 3.3 70B (Dec 2024) matching 405B-level quality at a fraction of the cost.

Why it matters

Llama 3.1 405B was the first openly downloadable model at GPT-4 class, trained on 15T+ tokens across 16,000 H100s, and Llama 3.3 70B then delivered near-405B quality at a fraction of the cost. The 3.2 1B/3B edge models and 11B/90B vision variants made Llama the default open stack from phones to clusters.

Facts

Try it yourself

Lineage

Descends fromLlama 2
Led toLlama 4Llama StackQuantized Llama 3.2

See the whole family tree →

Sources

More in Language & LLMs

Large Concept ModelsByte Latent TransformerCoconutMulti-token predictionMemory Layers at ScaleLLaMA

Read the Language & LLMs story on the sky →

✦ Open on the map Explore Language & LLMs Quiz me