|
first LoRA that actually helped
|
09-15-2026, 07:34 AM
Appreciate the detail. I ended up in about the same place using LM Studio. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing. I keep promising myself this is the last rebuild.
2x3090 • llama.cpp • too much VRAM is still not enough
|
|
« Next Oldest | Next Newest »
|
| Messages In This Thread |
|
first LoRA that actually helped - by cudascope - 09-15-2026, 03:21 AM
Re: first LoRA that actually helped - by vrambandit - 09-15-2026, 07:34 AM
Re: first LoRA that actually helped - by benchplease - 09-15-2026, 01:53 PM
Re: first LoRA that actually helped - by localtinker - 09-15-2026, 09:52 AM
Re: first LoRA that actually helped - by batchpeak - 09-18-2026, 02:14 PM
Re: first LoRA that actually helped - by quiethouse - 09-20-2026, 02:57 AM
Re: first LoRA that actually helped - by routearch - 09-20-2026, 05:22 AM
Re: first LoRA that actually helped - by benchplease - 09-21-2026, 05:34 PM
|
