Inference › RAG & Knowledge Systems › RAG v
hybrid retrieval results

Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Threaded Mode
hybrid retrieval results
sparrowbrook Offline
Junior Member
**
Posts: 15
Threads: 3
Joined: Sep 2026
Reputation: 0
#11
09-16-2026, 06:45 AM
Interesting, I hadn't tried that. That matches what I saw on mini PC. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.
Find
Reply
circuitworks90 Offline
Junior Member
**
Posts: 36
Threads: 2
Joined: Sep 2026
Reputation: 0
#12
09-16-2026, 07:23 AM
Interesting, I hadn't tried that. That matches what I saw on dual 3090. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.
Find
Reply
mangohouse Offline
Junior Member
**
Posts: 34
Threads: 2
Joined: Sep 2026
Reputation: 0
#13
09-16-2026, 07:51 AM
Maybe, but I had the opposite result. I get why that seems right, but on B200 the bottleneck felt elsewhere. Could be a workload difference, but I wouldn't generalize too fast from one setup.
small models can still be good
Find
Reply


Forum Jump:


Users browsing this thread: 2 Guest(s)