10-01-2026, 11:10 AM
Interesting, I hadn't tried that. The pattern around token cost has been pretty similar for me. The biggest change for me was simplifying the stack instead of adding one more optimization layer.
Inference
›
Inference Engines
›
Ollama / LM Studio / Desktop Runtimes
best local runtime for mixed models
best local runtime for mixed models
|
best local runtime for mixed models
|
|
« Next Oldest | Next Newest »
|
| Messages In This Thread |
|
best local runtime for mixed models - by mellowwire98 - 09-30-2026, 10:09 PM
Re: best local runtime for mixed models - by vectorpoint - 10-01-2026, 10:35 AM
Re: best local runtime for mixed models - by vectorhouse71 - 10-01-2026, 11:10 AM
Re: best local runtime for mixed models - by mellowwire98 - 10-01-2026, 11:50 AM
Re: best local runtime for mixed models - by thetanest - 10-02-2026, 12:31 PM
Re: best local runtime for mixed models - by papermixer4 - 10-02-2026, 04:38 PM
Re: best local runtime for mixed models - by vectorember - 10-02-2026, 06:43 PM
Re: best local runtime for mixed models - by vrambandit - 10-03-2026, 07:09 PM
|
Users browsing this thread: 1 Guest(s)