Strands Decider 2B: A 2B-Parameter Decision Model That Runs on Your Laptop

Strands Decider 2B: a small, open-source, decision model

Strands Decider 2B: A 2B-Parameter Decision Model That Runs on Your Laptop

Strands Labs has released Strands Decider 2B, a 2-billion-parameter open-source decision model that picks among options and assigns confidence scores. It runs locally on CPU or GPU with median latency around 115ms on an RTX 3090 and 153ms on an M3 MacBook. Built by replacing an LLM's text-generation head with a pointer head, it's designed for agentic workflows like tool selection, routing, and guardrails. Weights, training data, and scripts are on GitHub and Hugging Face.

The point is that a decision this cheap can sit in a path where an LLM call never could.
  1. girvo

    Does anyone know if it is worth fine-tuning one of these decision models on the shape of the questions you want it to work on, vs the more general versions? I'm using Jev pretty successfully at work at the moment, but am curious about what is doable

  2. real_faxenoff

    As a regular user of a bunch of specialized micromodels, I'll tell you this: you won't be happy with such a model (and its JEV counterparts) running permanently in the background on your PC's CPU. You need to offload their processing to the NPU. There are many pitfalls along the way, but the result is worth it.

    NPU performance will be twice as high, while power consumption will be four times lower. No additional fan noise (if you know what I mean).

    I'll wait another month until the first phase of the =battle royale= among models of this kind wraps up, put together a solution for the NPU/iGPU, and post it on HF.

  3. adenta

    At this point I can't wait for a comedian to release a decision model backed by humans.

    Meet Jerry- it's literally a guy named Jerry answering your questions.

  4. mynti

    Can someone explain this architecture a bit more in depth? They say the pointer head scores the hidden state at each option against the hidden state of the answer. But the LLM produces hidden states per token, so an option can span multiple tokens, no?

  5. mattvr

    Why is everyone calling binary choices `noul`? Does this have some meaning or is it just copying Jev’s API?

More from this day

2026-10-07