Back to Models

Llama 4 Scout 17B 16E Instruct

Llama 4 Scout variant with 17B parameters and mixture-of-experts architecture for efficiency

Parameters
170 B
Context
128,000 tokens
Released
Apr 1, 2025

Leaderboards

Average Score combining domain-specific Autobench scores; Higher is better

Performance vs. Industry Average

Context Window

Llama 4 Scout 17B 16E Instruct has a smaller context window than average (406k tokens), with a context window of 128k tokens.

Llama 4 Scout 17B 16E Instruct - AutoBench