10-06-2026, 09:16 PM
What worked for me was pretty simple. On dual 3090, 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 with Ollama
best local runtime for mixed models with Ollama
|
best local runtime for mixed models with Ollama
|
|
« Next Oldest | Next Newest »
|
| Messages In This Thread |
|
best local runtime for mixed models with Ollama - by fusedhall - 10-04-2026, 07:02 PM
Re: best local runtime for mixed models with Ollama - by rocmcrate26 - 10-04-2026, 08:47 PM
Re: best local runtime for mixed models with Ollama - by mellowwire98 - 10-04-2026, 11:24 PM
Re: best local runtime for mixed models with Ollama - by orbitbench6 - 10-04-2026, 11:53 PM
Re: best local runtime for mixed models with Ollama - by vectorember - 10-05-2026, 08:20 AM
Re: best local runtime for mixed models with Ollama - by amberhall - 10-05-2026, 08:38 AM
Re: best local runtime for mixed models with Ollama - by mellowwire98 - 10-06-2026, 09:16 PM
Re: best local runtime for mixed models with Ollama - by amberhall - 10-07-2026, 01:23 AM
Re: best local runtime for mixed models with Ollama - by vectorember - 10-08-2026, 01:54 AM
Re: best local runtime for mixed models with Ollama - by fusedhall - 10-08-2026, 04:07 AM
|
Users browsing this thread: 1 Guest(s)