Show HN: Light like the Terminal – Meet GTK LLM Chat Front End

Post by cma » Mon, Apr 21, 2025, 9:10 PM UTC

cma wrote: post #7

guessmyname wrote: post #4

It’d be better if it was written in C or at least Vala. With Python, you have to wait a couple hundred milliseconds for the interpreter to start, which makes it feel less native than it can be. That said, the latency of the LLM responses is higher than the UI, so I guess the slowness of Python doesn’t matter.

What's the startup time now with 9950X3D, after a prior start so the pyc's are cached in RAM?

Post by icarito » Tue, Apr 22, 2025, 4:26 PM UTC

cma wrote: post #7

guessmyname wrote: post #4

It’d be better if it was written in C or at least Vala. With Python, you have to wait a couple hundred milliseconds for the interpreter to start, which makes it feel less native than it can be. That said, the latency of the LLM responses is higher than the UI, so I guess the slowness of Python doesn’t matter.

What's the startup time now with 9950X3D, after a prior start so the pyc's are cached in RAM?

Post by cma » Wed, Apr 23, 2025, 2:50 AM UTC

icarito wrote: post #13

cma wrote: post #7

Earlier quoted context omitted.

What's the startup time now with 9950X3D, after a prior start so the pyc's are cached in RAM?

Hey I felt bad that there was a longer delay and by making sure to lazy-load everything I could, I managed to bring down the startup time from 2.2 seconds to 0.6 on my machine! Massive improvement! Thanks for the challenge!