+- 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: whisper alternatives lately on M3 Max (/showthread.php?tid=1164)
Pages:
1
2
Re: whisper alternatives lately on M3 Max - cudascope - 10-19-2026
Good point. That matches what I saw on B200. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.
Re: whisper alternatives lately on M3 Max - visionforge - 10-19-2026
Need a little more detail here. Do you see the same thing with a smaller batch or shorter prompt?
Re: whisper alternatives lately on M3 Max - quiethouse - 10-19-2026
Thanks, that helps. I ended up in about the same place using Ollama. The biggest change for me was simplifying the stack instead of adding one more optimization layer.
Re: whisper alternatives lately on M3 Max - vectorfield - 10-19-2026
Thanks, that helps. I ended up in about the same place using llama.cpp. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.