+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Edge AI & Gadgets (https://www.datasculpting.ai/inference/forumdisplay.php?fid=21)
+--- Forum: Mobile (https://www.datasculpting.ai/inference/forumdisplay.php?fid=73)
+--- Thread: on-device inference worth the effort (/showthread.php?tid=187)
Pages:
1
2
Re: on-device inference worth the effort - plainline - 09-20-2026
A couple things I'd check first. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at tool calling. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
Re: on-device inference worth the effort - promptspark58 - 09-20-2026
subscribed, curious where this lands.
Re: on-device inference worth the effort - amberrunner - 09-20-2026
A couple things I'd check first. Before rebuilding anything, I'd test one clean baseline with Kimi and compare from there. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
I'm happy to test one more variant if you want a second data point.