+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Drivers / Frameworks / Toolkits (https://www.datasculpting.ai/inference/forumdisplay.php?fid=8)
+--- Forum: Apple / MLX (https://www.datasculpting.ai/inference/forumdisplay.php?fid=33)
+--- Thread: MLX model loading quirks for Phi (/showthread.php?tid=247)
MLX model loading quirks for Phi - quantsupply - 09-13-2026
I figured I'd ask here before changing everything.
I'm trying to decide whether to keep the current stack or change course. Main question is how people here are handling small local stacks.
Would appreciate practical advice rather than theory.
Re: MLX model loading quirks for Phi - circuitwire58 - 09-13-2026
A couple questions before I guess too hard. Do you see the same thing with a smaller batch or shorter prompt?