Small models are improving and becoming more capable. The quality of local LLMs is basically unbounded. The context size of local LLMs is bounded by hardware. So local LLMs can be very capable for small, self-contained tasks.

qwen 3.6 35b running locally:

Write a Python script that can pull weather data from public sources and provide the high and low temperature for the current day in Miami, FL.

Single shot. No tool/internet use, so it didn’t pull this script from elsewhere.

import requests

def get_miami_weather():
    # Miami, FL coordinates
    LATITUDE = 25.7617
    LONGITUDE = -80.1918

    # Open-Meteo API URL (free, no API key required)
    url = (
        f"https://api.open-meteo.com/v1/forecast?"
        f"latitude={LATITUDE}&longitude={LONGITUDE}"
        f"&daily=temperature_2m_max,temperature_2m_min"
        f"&timezone=auto"
    )

    try:
        response = requests.get(url, timeout=10)
        response.raise_for_status()  # Raises error for 4xx/5xx HTTP status codes
        data = response.json()

        # Index 0 corresponds to the current day
        high_c = data["daily"]["temperature_2m_max"][0]
        low_c = data["daily"]["temperature_2m_min"][0]

        # Convert to Fahrenheit (commonly used in the US)
        high_f = (high_c * 9/5) + 32
        low_f = (low_c * 9/5) + 32

        print("🌤️  Miami, FL Weather for Today:")
        print(f"High: {high_f:.1f}°F ({high_c:.1f}°C)")
        print(f"Low:  {low_f:.1f}°F ({low_c:.1f}°C)")

    except requests.exceptions.HTTPError as http_err:
        print(f"❌ HTTP error occurred: {http_err}")
    except requests.exceptions.ConnectionError:
        print("❌ Error: Could not connect to the weather API.")
    except requests.exceptions.Timeout:
        print("❌ Error: Request timed out.")
    except requests.exceptions.RequestException as err:
        print(f"❌ An error occurred: {err}")
    except KeyError as key_err:
        print(f"❌ Error parsing data: Missing expected key {key_err}")
    except Exception as err:
        print(f"❌ Unexpected error: {err}")

if __name__ == "__main__":
    get_miami_weather()

Output:

% python3 ./m_weather.py
🌤️  Miami, FL Weather for Today:
High: 88.0°F (31.1°C)
Low:  73.2°F (22.9°C)

I tried to keep the size and scope within something that would reasonably fit in a comment. Looks pretty decent to me, but I can’t write Python myself. Never learned. I double-checked the LAT & LON of Miami, and it’s spot on.

It did take 47 seconds, while a cloud LLM would probably take 5 or less.

All I’m saying is local LLM isn’t garbage and it is getting better all the time.

Sorry, but I think the point about local AI not necessarily being evil is the tangent here.

The OP is about motherboard shortages, which is being driven by the big AI companies and is making hardware unaffordable for normal users

The top level reply to that is about how that’s bad because it removes the ability for people to be in control of their own computing

Then someone comes in, saying “yeah, but you can host your own AI so that it’s not evil so not all AI is bad”

Then someone points out that you can only host your AI if you can afford the hardware to do so which, as the OP and the comment you replied to pointed out, is getting really hard to do.

Only when you ignore what was literally the first premise and conclusion.

Correct… so when I tell you “guns DON’T kill people, people kill people” you are right to assume and I am just an idiot trying to jingle keys in front of you to distract you from the fact that guns do in fact kill people.

The models you can run on consumer hardware are still nowhere near the stuff that runs in corporate data centers. To stick with your metaphor, its like running a little steam engine at home while the big guys get to operate nuclear reactors…