HEAD TO HEAD
Jared Palmer: kev and StartLux: startlux-decision, compared on what they decide, where they run, what they cost and what their publishers report.
| Property | jared-palmer/kev | startlux/startlux-decision |
|---|---|---|
| Summary | An open family of System One models. A LoRA adapter plus a pointer head on a frozen Qwen base returns a distribution per typed question in one forward pass, serves TypeSafe's /v1/systemone contract, and ships a fitted temperature with every checkpoint. | 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, score, noul, classify, route | choice, score, noul |
| Architecture | kev | startlux-decision |
| Fine-tuned from | qwen/qwen3.5-4b-base | — |
| License | apache-2.0 | cc-by-nc-4.0 |
| Availability | Open weights | Open weights |
| Hosted by | — | — |
| Input price | — | — |
| Decision accuracy | 83.8% | 88.3% |
| Calibration error | 0.042 | — |
| Valid action rate | — | — |
| Median latency | — | 26 ms |
| p95 latency | — | — |
| Evaluation suite | transfer-v4 (locked, out of domain) | JevBench public set (231 items; 204 correct), maker's run |
| Latest version | 2026.09 | 2026.10 |
| Variants | — | LICENSE, NOTICE, startlux_decision |
| Size of latest version | 152.2 MB | 8.7 GB |
| Files | 11 | 23 |
| Downloads | 1 | 3 |
| Stars | 0 | 0 |
| Tags | system-one, qwen, lora, pointer-head, 4b | 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.
kev is from Jared Palmer and startlux-decision from StartLux. Both have open weights you can download and run. Both answer choice, score and noul questions. Only kev answers classify and route. startlux-decision reads up to 256K tokens of state, against 8K tokens for kev. kev is the smaller model, at 4.0B parameters to 4.7B. kev is licensed apache-2.0; startlux-decision, cc-by-nc-4.0.
They report on different suites — kev 83.8% on transfer-v4 (locked, out of domain), 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.
kev: Free (open weights). startlux-decision: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Yes, both: systemone pull jared-palmer/kev and systemone pull startlux/startlux-decision download the weights.