+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Generative AI (https://www.datasculpting.ai/inference/forumdisplay.php?fid=17)
+--- Forum: Image (https://www.datasculpting.ai/inference/forumdisplay.php?fid=69)
+--- Thread: small speech stack for local use: anyone testing this? (/showthread.php?tid=203)
Pages:
1
2
Re: small speech stack for local use: anyone testing this? - amberpatch25 - 09-17-2026
A couple things I'd check first. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at structured output. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
Re: small speech stack for local use: anyone testing this? - quiethouse - 09-17-2026
That matches what I was seeing. The pattern around router policy has been pretty similar for me. The biggest change for me was simplifying the stack instead of adding one more optimization layer.
Re: small speech stack for local use: anyone testing this? - vectorfield - 09-21-2026
I tested this tonight. I couldn't reproduce the slowdown until I pushed context much higher. The surprise was that memory pressure showed up before throughput collapsed.
Re: small speech stack for local use: anyone testing this? - vramarch - 09-22-2026
What worked for me was pretty simple. If you're on MLX, I'd confirm the version first and then reduce variables until the behavior is obvious. Once you know the plain path works, then add the faster path back in piece by piece.
Re: small speech stack for local use: anyone testing this? - quantyard - 09-22-2026
That matches what I was seeing. That matches what I saw on 4090. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
Re: small speech stack for local use: anyone testing this? - kernelpeak - 09-22-2026
What worked for me was pretty simple. If you're on MLX, I'd confirm the version first and then reduce variables until the behavior is obvious.