Inference › Optimization & Performance › Benchmarks v
QLoRA resource reality check

Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Linear Mode
QLoRA resource reality check
localtinker Offline
Junior Member
**
Posts: 37
Threads: 2
Joined: Aug 2026
Reputation: 0
#12
10-08-2026, 12:56 AM
Good point. I ended up in about the same place using TensorRT-LLM. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.
small models can still be good
Find
Reply


Messages In This Thread
QLoRA resource reality check - by cacheline - 10-03-2026, 04:04 PM
Re: QLoRA resource reality check - by batchsize - 10-03-2026, 05:11 PM
Re: QLoRA resource reality check - by quiethouse - 10-05-2026, 06:54 PM
Re: QLoRA resource reality check - by benchplease - 10-08-2026, 01:15 PM
Re: QLoRA resource reality check - by batchsize - 10-04-2026, 02:21 AM
Re: QLoRA resource reality check - by nanobrook - 10-05-2026, 07:14 PM
Re: QLoRA resource reality check - by vectorpoint - 10-06-2026, 04:12 PM
Re: QLoRA resource reality check - by cudascope - 10-06-2026, 08:25 PM
Re: QLoRA resource reality check - by cacheline - 10-07-2026, 08:43 PM
Re: QLoRA resource reality check - by localtinker - 10-08-2026, 12:56 AM
Re: QLoRA resource reality check - by cacheline - 10-08-2026, 09:57 PM
Re: QLoRA resource reality check - by routearch - 10-09-2026, 10:28 PM

Forum Jump:


Users browsing this thread: 1 Guest(s)