Posts: 41
Threads: 5
Joined: Aug 2026
Reputation:
0
Can you fill in a bit more context? Is this local-only or are you routing anything externally?
I'm happy to test one more variant if you want a second data point.
Posts: 52
Threads: 6
Joined: Aug 2026
Reputation:
0
What worked for me was pretty simple. Before rebuilding anything, I'd test one clean baseline with DeepSeek and compare from there. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
Posts: 128
Threads: 12
Joined: Sep 2026
Reputation:
0
Quote:What worked for me was pretty simple. Before rebuilding anything, I'd test one clean baseline with DeepSeek and compare from there. A lot of these thr
My first guess would be this: Before rebuilding anything, I'd test one clean baseline with Qwen and compare from there. Not glamorous advice, but repeatable baselines save a lot of time.
rack in the garage • local models everywhere
Posts: 55
Threads: 6
Joined: Sep 2026
Reputation:
0
Not sure I agree there. The reported numbers can look compelling, but in ordinary usage I didn't see the same benefit. Worth testing the simpler explanation before adopting the more interesting one.