All models

COMPARE

2 models, side by side.

What each one decides, how well calibrated it is, how fast it answers and what it costs to pull. Up to 4 at a time; the better value in each row is marked.

Propertymapika/decideralibi-serikbay/jevk5
SummaryThe most-downloaded open System One reproduction. Merged Qwen3.5 fine-tunes, trained on about 95 public decision sets, then calibration-aware RL and a rank-64 LoRA, that softmax letter logits at an answer slot.Qwen3.5-4B with a merged rank-16 LoRA distilled from 17,408 teacher questions and 30,000 public training rows, read out as a temperature-scaled softmax over answer-letter logits. Also in 9B, 2B and GGUF.
Decideschoice, score, noul, classify, routechoice, score, noul, classify, route
Architecturedeciderjevk5
Fine-tuned fromqwen/qwen3.5-2b-baseqwen/qwen3.5-4b
Licenseapache-2.0apache-2.0
AvailabilityOpen weightsOpen weights
Hosted by——
Input price——
Decision accuracy80.2%78.4%
Calibration error0.0380.035
Valid action rate——
Median latency3.2 ms13.2 ms
p95 latency——
Evaluation suiteDecider 67-task regression setJevBench public hard tier
Latest version2026.090.3.0
Variants—SHA256SUMS
Size of latest version3.5 GB7.9 GB
Files48
Downloads00
Stars00
Tagssystem-one, qwen, rl, calibrated, 2bsystem-one, qwen, lora, distilled, 4b
UpdatedSep 25, 2026Sep 25, 2026