+- 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: human evals on small teams on mini PC (/showthread.php?tid=868)
Pages:
1
2
human evals on small teams on mini PC - fastbench - 10-07-2026
Spent some time on this today and wanted to compare notes.
I've gone back and forth between SGLang and vLLM for DeepSeek. The interesting difference for me has been reranking.
Interested in tradeoffs more than fan loyalty.
Re: human evals on small teams on mini PC - cacheline - 10-09-2026
that fixed it for me too.
Re: human evals on small teams on mini PC - promptpoint - 10-09-2026
Appreciate the detail. I don't think your conclusion is far off. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
Re: human evals on small teams on mini PC - deltagrid - 10-09-2026
same here on my side.
Re: human evals on small teams on mini PC - macropoint - 10-09-2026
Maybe, but I had the opposite result. I've seen people blame consumer GPUs when the real issue was much more mundane.
Re: human evals on small teams on mini PC - modgarden - 10-10-2026
Interesting, I hadn't tried that. I ended up in about the same place using Ollama. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
Re: human evals on small teams on mini PC - cacheline - 10-13-2026
That matches what I was seeing. The pattern around embeddings 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.
Re: human evals on small teams on mini PC - latentcraft - 10-16-2026
What worked for me was pretty simple. Before rebuilding anything, I'd test one clean baseline with DeepSeek and compare from there. Not glamorous advice, but repeatable baselines save a lot of time.
Re: human evals on small teams on mini PC - nanogarden - 10-17-2026
worth checking the driver first.
Re: human evals on small teams on mini PC - bytegarden73 - 10-17-2026
Tried to reproduce it just now. My result was mixed: first run looked bad, second run looked normal. The main thing that moved was latency, not quality.