Inference › Optimization & Performance › Benchmarks v
first LoRA that actually helped: early impressions

Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Linear Mode
first LoRA that actually helped: early impressions
batchsize Offline
Member
***
Posts: 137
Threads: 16
Joined: Sep 2026
Reputation: 0
#3
10-18-2026, 10:56 PM
Good point. I ended up in about the same place using MLX. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
throughput matters, but tail latency matters too
Find
Reply


Messages In This Thread
Re: first LoRA that actually helped: early impressions - by batchsize - 10-18-2026, 10:56 PM

Forum Jump:


Users browsing this thread: 1 Guest(s)