10-19-2026, 12:38 AM
I tested this tonight. On M3 Max with vLLM, I saw basically the same behavior. I expected the model choice to matter more than it did.
Inference
›
Training & Customization
›
Fine-Tuning / LoRA
workflow automation with local models on dual 3090
workflow automation with local models on dual 3090
|
workflow automation with local models on dual 3090
|
|
« Next Oldest | Next Newest »
|
| Messages In This Thread |
|
workflow automation with local models on dual 3090 - by northgrid33 - 10-15-2026, 02:56 AM
Re: workflow automation with local models on dual 3090 - by phasestream53 - 10-15-2026, 03:39 AM
Re: workflow automation with local models on dual 3090 - by northgrid33 - 10-16-2026, 03:50 PM
Re: workflow automation with local models on dual 3090 - by southden - 10-16-2026, 05:34 PM
Re: workflow automation with local models on dual 3090 - by labline - 10-17-2026, 06:21 AM
Re: workflow automation with local models on dual 3090 - by mintstation99 - 10-19-2026, 12:04 AM
Re: workflow automation with local models on dual 3090 - by ggufvault - 10-19-2026, 12:38 AM
Re: workflow automation with local models on dual 3090 - by bytegarden73 - 10-19-2026, 01:20 AM
Re: workflow automation with local models on dual 3090 - by llm_wren - 10-19-2026, 01:20 AM
Re: workflow automation with local models on dual 3090 - by thetanest - 10-19-2026, 03:34 AM
|
Users browsing this thread: 1 Guest(s)