v1.1, October 2026. Read-or-Think: one-pass answer, a short thought only when unsure. 4B, 9B, 27B.
AI & ML interests
None defined yet.
Recent Activity
Papers
DecisionPivot: A Diagnostic Benchmark for Decision Models in LLM Systems
StartLux-Decision: AutoThink Decision Models with Reinforcement Learning for Calibrated Deliberative Decisions
models 65
startlux-models/ReaDy-Qwen3.8-27B
Text Generation • 2B • Updated • 216 • 4
startlux-models/StartLux-Decision-v1.1-9B-Instant
10B • Updated • 5.44k • 2
startlux-models/StartLux-Decision-v1.1-9B-AutoThink
9B • Updated • 1.11k • 3
startlux-models/StartLux-Decision-v1.1-4B-Instant
5B • Updated • 2.22k • 8
startlux-models/StartLux-Decision-v1.1-4B-AutoThink
5B • Updated • 1.76k • 7
startlux-models/StartLux-Decision-v1.1-2B-Instant
2B • Updated • 1.07k • 2
startlux-models/StartLux-Decision-v1.1-27B-Instant
28B • Updated • 5.31k • 16
startlux-models/StartLux-Decision-v1.1-27B-AutoThink
27B • Updated • 1.98k • 12
startlux-models/StartLux-Decision-v1.1-0.8B-Instant
0.9B • Updated • 1.91k • 4
startlux-models/StartLux-Decision-v1.1-9B-Instant-MLX-8bit
9B • Updated • 372 • 1