Inference
quality tests for local assistants for Mistral - Printable Version

+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Evaluation & Testing (https://www.datasculpting.ai/inference/forumdisplay.php?fid=16)
+--- Forum: Evals (https://www.datasculpting.ai/inference/forumdisplay.php?fid=66)
+--- Thread: quality tests for local assistants for Mistral (/showthread.php?tid=1286)

Pages: 1 2


Re: quality tests for local assistants for Mistral - oxidestream - 10-18-2026

Good point. I don't think your conclusion is far off.


Re: quality tests for local assistants for Mistral - sparrowkite53 - 10-18-2026

Can you fill in a bit more context? Is this local-only or are you routing anything externally?


Re: quality tests for local assistants for Mistral - quietstack - 10-18-2026

Good point. That matches what I saw on 4090. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.


Re: quality tests for local assistants for Mistral - batchcraft - 10-19-2026

worth checking the driver first.


Re: quality tests for local assistants for Mistral - vectorhouse71 - 10-19-2026

Need a little more detail here. Do you see the same thing with a smaller batch or shorter prompt?