Green Stop: a Mumbai commute reset that runs on a local open-weight model

Description and use

Green Stop helps Mumbai commuters use spare commute time by suggesting nearby green spots that can be reached within the available minutes, all processed locally without cloud LLMs.

Problem

Mumbai commuters lose hours to traffic: a 1‑hour trip becomes 3. Telling tired people to "go touch grass" after that doesn't work, since nobody wants a detour.

Outcome

Green Stop provides commuters with a precise green spot that can be reached within their spare time, reducing extra commute time and improving mood.

Workflow

• User enters current location and minutes spare
• Python geocodes location via OpenStreetMap Nominatim
• Python matches to hand‑picked CSV spots and OSM parks/gardens/beaches
• Python calculates walk distance (to spot + 5 min break + back) using straight‑line distance ×1.3 at 5 km/h
• Python builds facts card
• Gemma 3 4B via Ollama generates a 2‑sentence friendly note
• Gradio UI displays card and Google Maps walking‑directions link

Evidence

Mumbai commuters lose hours to traffic: a 1-hour trip becomes 3.

Source

Green Stop takes where you are and how many minutes you can spare. It finds a green spot you can walk to and back in that time and gives you: the spot's name and full address, walking time and total time needed, live temperature and AQI, a Google Maps walking-directions link, a short friendly note from a local LLM, in English, Hindi or Marathi

Source

Python finds the facts and the LLM only adds a human note.

Source

The model runs on my laptop and the app has no accounts, no tracking and no cloud LLM. The place cache stays local.

Source

I tested Green Stop on my own commute from [10th Oct]. Here is a real run: Input: Marine Lines Station, Mumbai, [50] minutes, English

Source

The address was not precise. OpenStreetMap's reverse lookup returned "Mumbai Coastal Road - Phase I, Navjeevan Wadi, Kalbadevi..." instead of "Marine Drive".

Source