10-06-2026, 06:31 PM
I tested this tonight. The issue went away once I changed one setting and restarted the stack cleanly. I expected the model choice to matter more than it did.
small models can still be good
|
RTX 5090 local inference
|
|
« Next Oldest | Next Newest »
|
| Messages In This Thread |
|
RTX 5090 local inference - by turbogrid11 - 09-29-2026, 09:49 PM
Re: RTX 5090 local inference - by cudapoint - 09-30-2026, 12:13 AM
Re: RTX 5090 local inference - by embersmith - 09-30-2026, 12:31 AM
Re: RTX 5090 local inference - by cudapoint - 09-30-2026, 12:47 PM
Re: RTX 5090 local inference - by nanobrook - 10-03-2026, 04:46 PM
Re: RTX 5090 local inference - by sanevault - 10-06-2026, 06:31 PM
Re: RTX 5090 local inference - by batchwire - 10-03-2026, 01:22 PM
Re: RTX 5090 local inference - by routeforge64 - 10-03-2026, 01:57 PM
Re: RTX 5090 local inference - by signaltrack44 - 10-03-2026, 03:59 PM
Re: RTX 5090 local inference - by rocmriley - 10-03-2026, 06:05 PM
Re: RTX 5090 local inference - by paperrunner - 10-03-2026, 06:17 PM
Re: RTX 5090 local inference - by circuitwire58 - 10-07-2026, 06:36 AM
Re: RTX 5090 local inference - by dockkite69 - 10-07-2026, 07:02 AM
|
Users browsing this thread: 1 Guest(s)