Strands Decider 2B (hobson-v21) — VRAM & /v1/systemone setup
Written by Jakub Rusinowski · Last updated
AWS Strands Labs' 2B decision model: Qwen3.5-2B-Base without its language-model head, a LoRA and a small readout head. Apache-2.0; pip install strands-decider, then strands-decider serve at /v1/systemone.
Strands Decider 2B (hobson-v21) needs about 2 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache. On Apple Silicon that figure comes out of unified memory.
Call Strands Decider 2B (hobson-v21)
Served by strands-decider serve (default port 8000). This model does not run in Ollama.
- Question types
- choice noul (yes / no) score
- Inputs
- text
- Serve with
strands-decider serve- Endpoint
/v1/systemone
pip install strands-deciderstrands-decider serve StrandsAgents/strands-decider-2B-hobson-v21 --port 8000http://localhost:8000/v1/systemone
Setup for servers other than Ollama →
Build a request for this model Decision models guide
Related guides: Servers other than Ollama · Confidence, thresholds and calibration
Other decision models: Nimble 9B · Tev1 4B · Tev1 0.8B · Winnow 12B · Winnow E4B · Decider 2B · Decider 4B · Decider 35B-A3B (NVFP4) · Decider 12B Vision · Decider 31B v2 (NVFP4) · JevK5 4B · Intern-Decision 4B · AutoJev 27B · Laya · Clef 27B · Clef-Flash 9B · Rune 26B-A4B v3 · OpenDecider-nano · OpenDecider-small · OpenDecider-small MLX 4-bit · Bosun v3.1 0.6B · Bosun v3.1 1.7B · d1-3B · d1-omni-600M · THX-01 322M · mammoth-1 27B · elephant-1 9B · kev 4B · kev 9B · OpenJev 27B
Hardware fit
Weights plus overhead plus the KV cache at a 8,192-token prompt, on NVIDIA RTX 4090 (24 GB). A publisher build is sized from its file; the other rows are modelled at a standard quant. Decision requests are short, so no long-context figure is shown.
| Quant | Memory | VRAM | Fit |
|---|---|---|---|
| Q4_K_M 4.83 bpw · modelled quant | 2.7 GB | Fits | |
| Q6_K 6.56 bpw · modelled quant | 3.1 GB | Fits | |
| Q8_0 8.50 bpw · modelled quant | 3.5 GB | Fits |
hobson-v21 is the checkpoint the Decision Index scores; the launch checkpoint was hobson-v19 (167 of 231 JevBench tasks).
How it was scored
Two different suites on two different scales. Never compare the numbers across the two cards.
Author's public benchmark
JevBench public (231 tasks, window 4096)Raw per-benchmark scores from the vendor's own internal run, not chance-corrected and not independently reproduced. They are not the Decision Index's balanced skill, so do not compare them with the card beside this one.
Source ↗Decision Index 0.4.1 (snapshot 2026-10-22)
Decision Index 0.4.1Community Decision Index (not by the model's authors)- ECE (lower is better)
- 0.0441
Community-maintained; not affiliated with the model authors.
Source ↗Decision models are not ranked on chat, creative or coding scores.
Specifications
Verified — Checked against the primary source — the model card or the vendor spec page — and corroborated by a second independent source.
- Parameters
- 1.9B
- Context window
- Not published
- Architecture
- Fine-tune of Qwen/Qwen3.5-2B-Base
- Provider
- AWS Strands Labs
- Licence
- Apache-2.0
- Availability
- Weights downloadable
- Practical deployment
- Edge device (phone, SBC)
- Specified at
- Q4_K_M
- System RAM
- 8 GB
- Record updated
- 2026-10-25
Commercial use permitted. No usage restrictions beyond attribution.
Strands Decider 2B (hobson-v21) — frequently asked questions
What is Strands Decider 2B (hobson-v21)?
Strands Decider 2B (hobson-v21) is a decision model: you send it a state and typed questions (choice, yes/no/unknown, or a score) and it returns one answer per question with a probability for every option. It is not a chat model.
How do I run Strands Decider 2B (hobson-v21) locally?
Served by strands-decider serve (default port 8000). This model does not run in Ollama. Start it with: `pip install strands-decider && strands-decider serve StrandsAgents/strands-decider-2B-hobson-v21 --port 8000`.
How much memory does Strands Decider 2B (hobson-v21) need?
About 2 GB for the weights plus overhead at Q4_K_M, before the prompt's KV cache. Decision prompts are short, so the cache stays small.
How accurate is Strands Decider 2B (hobson-v21)?
It has separate published scores on different suites — the community Decision Index 0.4.1 and the benchmarks listed on this page. They are not comparable with each other, and none is a calibration guarantee.