metaai·lightalo unofficial · independent
Universe / Language & LLMs / Llama 4
Language & LLMs · 2025

Llama 4

Llama 4 (Scout / Maverick / Behemoth)

A 10-million-token context window — and a turning point

open source superseded Scout 109B total / 17B active (16 experts); Maverick 400B total / 17B active (128 experts); Behemoth ~2T / 288B active (unreleased) params

Latest: Scout & Maverick (Apr 5, 2025); Behemoth never shipped — no Llama 4.x/5 followed

Meta's last open-weight frontier Llama generation, released April 5, 2025: natively multimodal mixture-of-experts models. Scout (17B active, 16 experts, 109B total) shipped with an unprecedented 10M-token context window; Maverick (17B active, 128 experts, 400B total) targeted flagship quality. Behemoth (~2T parameters, 288B active) was previewed but never released.

Why it matters

Llama 4 was Meta's last open frontier generation and the moment the strategy cracked: Scout's 10M-token context and native multimodality were genuine firsts for open weights, but the 2T-parameter Behemoth never shipped amid reported MoE-routing problems, and within a year Meta replaced the line with the closed Muse Spark.

Facts

Try it yourself

Lineage

Descends fromLlama 3 / 3.1 / 3.2 / 3.3
Led toMuse SparkLlama API

See the whole family tree →

Sources

More in Language & LLMs

Code World ModelLarge Concept ModelsByte Latent TransformerLlama StackCoconutMulti-token prediction

Read the Language & LLMs story on the sky →

✦ Open on the map Explore Language & LLMs Quiz me