10-05-2026, 03:21 AM
that fixed it for me too.
|
frontier API value lately with Ollama
|
|
10-05-2026, 03:21 AM
that fixed it for me too.
10-06-2026, 03:50 PM
Appreciate the detail. The pattern around quant drift has been pretty similar for me. The biggest change for me was simplifying the stack instead of adding one more optimization layer.
routing beats arguing over one perfect model
10-07-2026, 04:10 AM
What worked for me was pretty simple. Before rebuilding anything, I'd test one clean baseline with FLUX and compare from there. Not glamorous advice, but repeatable baselines save a lot of time.
10-07-2026, 08:43 AM
What exact setup are you running? What model, what runtime, and roughly what context size?
routing beats arguing over one perfect model
10-08-2026, 09:24 PM
What worked for me was pretty simple. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at long context.
|
|
« Next Oldest | Next Newest »
|