Inference › LLM Models › Proprietary / Frontier v
70B still worth the pain

Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Linear Mode
70B still worth the pain
phasetrack Offline
Junior Member
**
Posts: 32
Threads: 6
Joined: Sep 2026
Reputation: 0
#5
10-06-2026, 11:58 PM
Not sure I agree there. I wouldn't optimize around that first. On my side the bigger swing came from the runtime and not the model. Not saying you're wrong, just that I wouldn't lock that in as the lesson yet. At this point the real bottleneck is my patience.
Find
Reply


Messages In This Thread
70B still worth the pain - by cobaltworks25 - 10-06-2026, 05:33 PM
Re: 70B still worth the pain - by sanevault - 10-06-2026, 07:39 PM
Re: 70B still worth the pain - by latentscope35 - 10-06-2026, 08:51 PM
Re: 70B still worth the pain - by kernelghost - 10-06-2026, 09:28 PM
Re: 70B still worth the pain - by cacheline - 10-08-2026, 12:33 AM
Re: 70B still worth the pain - by plaingarden18 - 10-08-2026, 05:19 PM
Re: 70B still worth the pain - by phasetrack - 10-06-2026, 11:58 PM
Re: 70B still worth the pain - by mellowstream - 10-07-2026, 12:05 PM
Re: 70B still worth the pain - by tensorriver - 10-08-2026, 12:58 AM
Re: 70B still worth the pain - by macronest - 10-08-2026, 03:15 AM
Re: 70B still worth the pain - by macrolab - 10-08-2026, 03:42 AM
Re: 70B still worth the pain - by routeline23 - 10-08-2026, 04:44 AM
Re: 70B still worth the pain - by edgekite - 10-08-2026, 05:07 PM
Re: 70B still worth the pain - by deltastation - 10-11-2026, 05:46 PM

Forum Jump:


Users browsing this thread: 1 Guest(s)