Inference › Inference Engines › Ollama / LM Studio / Desktop Runtimes v
Ollama for power users

Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Linear Mode
Ollama for power users
edgeriver Offline
Junior Member
**
Posts: 40
Threads: 4
Joined: Sep 2026
Reputation: 0
#4
09-24-2026, 03:31 AM
Not sure I agree there. I've seen people blame prefill/decode split when the real issue was much more mundane. Could be a workload difference, but I wouldn't generalize too fast from one setup.
small models can still be good
Find
Reply


Messages In This Thread
Ollama for power users - by fusedhall - 09-23-2026, 04:56 AM
Re: Ollama for power users - by vectorember - 09-23-2026, 06:40 AM
Re: Ollama for power users - by visionyard23 - 09-23-2026, 07:30 PM
Re: Ollama for power users - by edgeriver - 09-24-2026, 03:31 AM
Re: Ollama for power users - by fusedhall - 09-24-2026, 11:31 AM
Re: Ollama for power users - by vectorhouse71 - 09-24-2026, 12:07 PM
Re: Ollama for power users - by vectorember - 09-25-2026, 12:40 PM
Re: Ollama for power users - by vectorcrate98 - 09-25-2026, 03:11 PM
Re: Ollama for power users - by quietstack - 09-28-2026, 03:46 PM
Re: Ollama for power users - by audionode8 - 09-29-2026, 12:13 AM
Re: Ollama for power users - by amberhall - 09-29-2026, 01:27 AM

Forum Jump:


Users browsing this thread: 1 Guest(s)