+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Miscellaneous Discussion (https://www.datasculpting.ai/inference/forumdisplay.php?fid=24)
+--- Forum: News & Industry (https://www.datasculpting.ai/inference/forumdisplay.php?fid=26)
+--- Thread: latest release actually worth attention (/showthread.php?tid=546)
latest release actually worth attention - deepseeked - 09-27-2026
Thought I'd post a small recipe because a lot of threads ask similar things.
Just sharing a setup that ended up working reasonably well: Mistral, LM Studio, dual 3090, with a lot of attention on tool calling.
Maybe useful as a starting point for newer folks.
Re: latest release actually worth attention - vectorpoint - 09-28-2026
worth checking the driver first.
Re: latest release actually worth attention - nanogarden - 09-28-2026
Good point. The pattern around router policy has been pretty similar for me.
Re: latest release actually worth attention - amberrunner - 09-29-2026
Ran a quick check on my box. The issue went away once I changed one setting and restarted the stack cleanly. The main thing that moved was latency, not quality.
Re: latest release actually worth attention - deepseeked - 09-29-2026
Interesting, I hadn't tried that. I ended up in about the same place using Ollama.
Re: latest release actually worth attention - promptspark58 - 09-30-2026
Interesting, I hadn't tried that. The pattern around batch size has been pretty similar for me. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.