10-19-2026, 02:07 AM
Quote:Did a bit of testing and thought I'd post the result here.
A couple things I'd check first. On 7900 XTX, the easiest win is often to back off the aggressive settings and see whether the problem survives.
Inference
›
Inference Engines
›
Ollama / LM Studio / Desktop Runtimes
best local runtime for mixed models: early impressions
best local runtime for mixed models: early impressions
|
best local runtime for mixed models: early impressions
|
|
« Next Oldest | Next Newest »
|
| Messages In This Thread |
|
best local runtime for mixed models: early impressions - by dockridge - 10-17-2026, 09:07 PM
Re: best local runtime for mixed models: early impressions - by fusedhall - 10-18-2026, 09:07 PM
Re: best local runtime for mixed models: early impressions - by vramforge - 10-18-2026, 10:30 PM
Re: best local runtime for mixed models: early impressions - by edgeriver - 10-18-2026, 11:25 PM
Re: best local runtime for mixed models: early impressions - by latentscope35 - 10-19-2026, 12:03 AM
Re: best local runtime for mixed models: early impressions - by localcraft17 - 10-19-2026, 01:09 AM
Re: best local runtime for mixed models: early impressions - by mellowwire98 - 10-19-2026, 02:07 AM
Re: best local runtime for mixed models: early impressions - by tensorkite - 10-19-2026, 02:07 AM
|
Users browsing this thread: 1 Guest(s)