Llama 4 Scout 17B Instruct

Open Llama with long-context vision for efficient multimodal agents

BENCHMARKS

Not in the Epoch Capabilities Index. Epoch benchmarks what it can run, so this is a gap in coverage, not a poor result.

RELEASE DATEApr 5, 2025
WEIGHTSOpen weights
CONTEXT WINDOW10M
MAX OUTPUT16.4K
REASONINGNo
TOOL CALLINGYes
INPUTStext, image
OUTPUTStext

Specifications from Models.dev. Availability and limits may differ by provider. Benchmark scores come from Epoch AI under CC BY 4.0.