# Strands Decider 2B v1 by Strands Labs

> Strands Decider 2B v1 scores typed questions with an open adapter and head. Read its runtime, three-run weight average and public benchmark results.

Updated 2026-11-12 (Australia/Adelaide)

## Quick answers

### What is Strands Decider 2B v1 by Strands Labs?

[Strands Decider 2B v1](<https://decisionmodels.ai/models/strands-decider>): A LoRA adapter and option-scoring head on Qwen3.5-2B-Base for Choice, Noul and Score questions.

[Strands Decider 2B v1 facts](<https://decisionmodels.ai/models/strands-decider>)

[Source](<https://huggingface.co/StrandsAgents/strands-decider-2B-qwen3.5-v1-2610>)

### Who makes Strands Decider 2B v1?

[Strands Decider 2B v1](<https://decisionmodels.ai/models/strands-decider>): Strands Labs

[Strands Decider 2B v1 facts](<https://decisionmodels.ai/models/strands-decider>)

[Source](<https://huggingface.co/StrandsAgents/strands-decider-2B-qwen3.5-v1-2610>)

By Strands Labs · Hugging Face weight release: 2026-10-09 · OPEN

A LoRA adapter and option-scoring head on Qwen3.5-2B-Base for Choice, Noul and Score questions. This v1 release averages three training runs and supplies a System One server. Its optional vision path keeps the base vision tower without image training. The community SageMaker project deploys the separate Strands Decider 2B hobson-v19 checkpoint.

## Facts

- Base: Qwen/Qwen3.5-2B-Base; separate base download required
- Inputs: Text; optional image path needs the vision extra and a runtime release after 0.1.0
- Runtime: strands-decider Python package, CPU, MPS or CUDA; POST /v1/systemone
- Licence: Apache-2.0; LICENSE.md included

## Claims and sources

- **VENDOR-REPORTED**: The maker reports 180/231 public [JevBench](<https://decisionmodels.ai/jevbench>) tasks correct at a 4,096-token serving window, Brier 0.280 and ECE 0.072. CPU and NVIDIA L4 select the same answers on all 231 tasks; the training harness differs on one near tie. These are maker runs, not an independently reproduced board score. [source](<https://huggingface.co/StrandsAgents/strands-decider-2B-qwen3.5-v1-2610>)

## Links

- [Source: Card, adapter and run records](<https://huggingface.co/StrandsAgents/strands-decider-2B-qwen3.5-v1-2610>)
- [Source: Licence](<https://huggingface.co/StrandsAgents/strands-decider-2B-qwen3.5-v1-2610/blob/main/LICENSE.md>)
- [Source: Runtime and training code](<https://github.com/strands-labs/strands-decider>)

## Camera test and hosting estimates

The camera-still report uses the existing v1 checkpoint, without new image training. Its 768 px Python path scores 85.2% at a test-selected cutoff. The HTTP path resizes to 448 px. Hosting costs depend on sustained volume; the reported L4 break-even is arithmetic without a measured L4 throughput run.

[Camera evidence](<https://decisionmodels.ai/#strands-camera>) · [Hosting utilisation example](<https://decisionmodels.ai/pricing#hosting-utilisation>)

[Source](<https://builder.aws.com/content/3GJlg7QPWdrYGQbeZVaowHNSTeo/classifying-images-with-strands-decider-2b-decision-model>)

## A separate E4B production deployment

Amazon’s ticket-labelling report uses a different Gemma 4 E4B checkpoint, not this 2B v1 model. The team describes SageMaker deployment with a shadow-comparison mode and a 45-second configuration rollback. Its reported cost depends on busy instances and shorter prompts; the published account supplies no raw tickets or held-out accuracy total.

[Production report and cost limits](<https://decisionmodels.ai/#strands-ticket-production>)

[Source](<https://strandsagents.com/blog/amazon-saves-millions-replacing-sonnet-with-strands-decider/>)

## Related projects

No related projects are listed in the registry.