Tech · strandsagents.com
Strands Decider 2B: a small, open-source, decision model
Compiled by KHAO Editorial — aggregated from 1 source. See llms.txt for citation guidance.
◌ Single Source
Unlike LLMs that can generate arbitrary output, decision models are designed to pick between sets of options (e.g. “Is the string ‘turn on the lights’ about the coffee machine?
Key facts
- Figure 3: Decision latency as a function of task size (in tokens), measured on a local Nvidia RTX 3090 against v18 of the model
- The core idea is that they take a pre-trained LLM torso (Qwen3.5-2B), and remove the LM head, taking away its ability to generate text
- They've found that strands-decider-2b performs well on accuracy and calibration ( 3rd of 33 in the 2B class, and 1st of 30 excluding the just-over-2B models )
- It’s a 2 billion parameter model, suitable for running on a local CPU or GPU, which can return answers to meaningful questions in tens of milliseconds
Summary
Earlier this year, they announced strands-labs, a place to get hands-on with state-of-the-art approaches to agentic AI. Strands decider is one of a new class of decision models or system one models, a type of model that has been gaining a lot of attention since TypeSafe AI’s launch of Jev earlier this month. In exchange for this reduction in flexibility, decision models are faster and more capable at a given size, always produce an answer from the selected options, and can run with low latency. The flip side is that this approach (generating all outputs in a single parallel pass) makes it significantly worse at solving complex problems than reasoning models, and its lack of ability to generate text makes it unsuited for coding, chatbots, document summarization, and other common LLM tasks. In addition, decision models give each decision a high-quality reliability score (i.e. “how sure can the reporter be that this yes/no is correct?