continker/Qwen3.5-2B-metro-v24
Text Generation • 2B • Updated • 33
MetroLLM-Bench v24
Qwen3.5 students (2B/4B/9B/27B) fine-tuned for MetroLLM-Bench, plus the live demo. A 2.6 GB student matches a frontier API offline.
-
-
continker/Qwen3.5-4B-metro-v24
Text Generation • 4B • Updated • 24 -
continker/Qwen3.5-9B-metro-v24
Text Generation • 9B • Updated • 27 -
continker/Qwen3.5-27B-metro-v24
Text Generation • 27B • Updated • 22 -
MetroLLM-Bench Demo
🚇Plan metro trips with AI and see routes on a map
-
MetroLLM-Bench: Evaluating Language Models as Transit Kiosk Runtimes
Paper • 2609.10016 • Published • 15