Back to Models

Llama 4 Maverick 17B Instruct

FP8-quantized 17B Llama 4 Maverick model optimized for deployment efficiency and speed

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

Leaderboards

Performance vs. Industry Average

Context Window

Llama 4 Maverick 17B Instruct has a smaller context window than average (246k tokens), with a context window of 128k tokens.

Llama 4 Maverick 17B Instruct - AutoBench