Strands Launches Open-Source Decider 2B for Low-Latency Local Agent Decisions

Strands launches the open-source Decider 2B model for low-latency local AI-agent decisions, reporting roughly 115 ms median latency on an Nvidia RTX 3090 and a top JevBench ranking among strictly 2B-parameter models.

• Strands launches Strands Decider 2B, an open-source 2-billion-parameter decision model for local, low-latency agent workflows.
• The model ranks third of 33 models in the 2B class on JevBench accuracy and calibration, and first of 30 when excluding just-over-2B models.
• Strands Decider 2B delivers roughly 115 ms median local decision latency on an Nvidia RTX 3090 and about 153 ms for small tasks on an M3 MacBook.