+- 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: anyone testing this? (/showthread.php?tid=14)
MLX model loading quirks: anyone testing this? - thetaarch43 - 08-23-2026
Thought I'd post a small recipe because a lot of threads ask similar things.
Maybe useful as a starting point: MLX on 7900 XTX, keeping HBM constraints in mind from the start.
If someone wants the exact settings I can clean them up and post them.
Re: MLX model loading quirks: anyone testing this? - plainember52 - 08-23-2026
What worked for me was pretty simple. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at prefix caching. Once you know the plain path works, then add the faster path back in piece by piece.