Loading comparison…
HEAD TO HEAD
Ruoxi Qiu: canopy-jev and StartLux: startlux-decision, compared on what they decide, where they run, what they cost and what their publishers report.
| Property | camellia86/canopy-jev | startlux/startlux-decision |
|---|---|---|
| Summary | Ruoxi Qiu's decision adapter for a frozen Qwen3.8-27B: a 6.3M-parameter LoRA on the last four text layers plus a numerical prior. One shared state feeds isolated question branches; each Choice, Noul or Score question returns probabilities with no generated tokens. | StartLux's decision family in six sizes, 0.8B to a 35B-A3B mixture of experts. All questions in a request are answered in one forward pass, with a probability for every option, through a TypeSafe /v1/systemone-compatible server. Text, JSON or images, up to 256K tokens. |
| Decides | choice, noul, score | choice, score, noul |
| Architecture | canopy-jev | startlux-decision |
| Fine-tuned from | qwen/qwen3.8-27b | — |
| License | apache-2.0 | cc-by-nc-4.0 |
| Availability | Open weights | Open weights |
| Hosted by | — | — |
| Input price | — | — |
| Decision accuracy | 87.4% | 88.3% |
| Calibration error | — | — |
| Valid action rate | — | — |
| Median latency | — | 26 ms |
| p95 latency | — | — |
| Evaluation suite | JevBench public set (231 items; 202 correct), the maker's own fresh zero-shot run with the upstream scorer | JevBench public set (231 items; 204 correct), maker's run |
| Latest version | 0.1.0 | 2026.10 |
| Variants | LICENSE, NOTICE, artifacts, licenses | LICENSE, NOTICE, startlux_decision |
| Size of latest version | 24.1 MB | 8.7 GB |
| Files | 11 | 23 |
| Downloads | 0 | 3 |
| Stars | 0 | 0 |
| Tags | system-one, qwen, lora, adapter, shared-state, 27b | system-one, qwen, non-commercial, gguf, cuda-graphs, vision, mlx, 4.7b |
| Updated | Oct 7, 2026 | Oct 7, 2026 |
Figures are from each model’s manifest; accuracy and latency are what the publishers report, on their own suites and hardware. Add a third model.
canopy-jev is from Ruoxi Qiu and startlux-decision from StartLux. Both have open weights you can download and run. Both answer choice, noul and score questions. startlux-decision is the smaller model, at 4.7B parameters to 27B. canopy-jev is licensed apache-2.0; startlux-decision, cc-by-nc-4.0.
They report on different suites — canopy-jev 87.4% on JevBench public set (231 items; 202 correct), the maker's own fresh zero-shot run with the upstream scorer, startlux-decision 88.3% on JevBench public set (231 items; 204 correct), maker's run — so the numbers do not rank them. Test both on your own labelled examples.
canopy-jev: Free (open weights). startlux-decision: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Yes, both: systemone pull camellia86/canopy-jev and systemone pull startlux/startlux-decision download the weights.