Strands Decider 2B: a small, open-source, decision model
gmays
107 points
21 comments
October 07, 2026
Related Discussions
Found 5 related stories in 87.8ms across 8,687 title embeddings via pgvector HNSW
- Nodd – Tiny, use-case-specific decision models that can run in browser yaszko · 21 pts · September 28, 2026 · 54% similar
- Strands Harness zuckerborg0101 · 134 pts · September 23, 2026 · 51% similar
- Clef: Open-weight decision models, and new RL fine-tuning platform jasondavies · 474 pts · October 01, 2026 · 51% similar
- Decisions API is in public beta chiefstorm · 219 pts · October 06, 2026 · 50% similar
- Does an open-weight decision model beat a hosted one? Jev vs. Laya Jmeg8r · 11 pts · September 22, 2026 · 48% similar
Discussion Highlights (10 comments)
miguelspizza
This is a great model. I've been running it on device in chrome extension to filter things like email. It is just the right mix of size, capability and speed to make it generally useful for adhoc bulk classification tasks. For those wanting to run it in browser: https://huggingface.co/alxnahas/strands-decider-2B-webgpu
keyle
Fantastically well written. It's rare for me to be able to understand what the AI gurus are talking about, and this was written by humans for humans. It can technically be used for a lot of use cases, I'd like people to chime in on ideas on this?
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.
davvie
Looks really nice, I think I could use it on my Mac mini for some smaller automations
teruakohatu
Any idea how well this would run on a CPU?
soltanov
Benchmark calibration does not establish reliability on unfamiliar production inputs.
yieldcrv
a strand type game
SubiculumCode
Are any of these multimodal yet? I'd love to try asking a model with calibrated probabilities to answer question like, "do these shapes match?". Sure, you can ask a LLM....
stephantul
2B being called small is such a sign of the times
mattvr
Why is everyone calling binary choices `noul`? Does this have some meaning or is it just copying Jev’s API?