It's multimodal for input, not output unfortunately.

Gotta push the limits. Also the readme says its multimodal, so I was expecting a jpg lol.

optimism

Gemma 3n models: designed for efficient execution on everyday devices

m0wer

Large Language Models are not suited for ASCII art. They tokenize the input and only generate tokens as output. They lose a lot of spatial information and are not really trained for aligning the characters of the output.

It's similar to painting with a hammer. A very skilled person might do something that resembles art, but a hammer is not really meant for that😂