Open source #Open models#AI agents Oct 12, 2026 · Originally published Oct 9

Amazon releases Strands decider models in 2B, 12B and 26B-A4B sizes under Apache 2.0

Small decision models for agents: they only choose and score, and every answer comes with a calibrated confidence.

Primary source Hugging Face model card (Amazon) · huggingface.co Read the original ↗

// Key points

  • Three question types: yes/no, one of N options, and a level on an ordered scale; listed uses include model routing, tool selection, argument checking, triage, guardrails and evaluations.
  • The 12B version is a LoRA adapter plus a readout head on gemma-4-12B-it; a 2B version on Qwen3.5 and a 26B-A4B version on Gemma 4 appeared the same day, all Apache 2.0.
  • The 12B version gets 200 of 231 tasks right on public JevBench, with Brier 0.173 and ECE 0.061; the card says confidence thresholds should be measured on your own traffic, and rephrasing a question often doesn’t change the answer.
  • strands-decider serve starts a local HTTP server that binds to 127.0.0.1 with no authentication.

Builder's takeLiquid AI, Cloudflare and now Amazon have shipped decision models within a week, so the category is real. For agent calls like which tool to use, whether arguments are valid and whether to block, I’d try the 2B version on routing in AI Interview first and, as the card advises, set confidence thresholds from my own traffic; the local server has no auth, so don’t expose it beyond the machine.

// Background · from #Open models

Full timeline →
  1. Oct 12 Qwen releases Qwen-Image-2.1-Turbo weights: a 7B image model that generates in 8 steps, under a research license
  2. Oct 12 Tencent releases Youtu-Parsing-Omni, a 5B omni-modal parsing model scoring 96.96 overall on OmniDocBench v1.6
  3. Oct 11 Cloudflare open-sources Clef-omni, a multimodal decision model, and cuts Clef-flash input from $0.09 to $0.038 per million tokens