Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
DeepSeek V4.1 impressions for Llama
#2
I don't think that's the whole story. I get why that seems right, but on dual 3090 the bottleneck felt elsewhere. Not saying you're wrong, just that I wouldn't lock that in as the lesson yet.
routing beats arguing over one perfect model
Reply


Messages In This Thread
Re: DeepSeek V4.1 impressions for Llama - by routecraft - 10-18-2026, 07:22 PM

Forum Jump:


Users browsing this thread: 1 Guest(s)