+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Harnesses, Agents & Orchestration (https://www.datasculpting.ai/inference/forumdisplay.php?fid=11)
+--- Forum: Workflows / Automation (https://www.datasculpting.ai/inference/forumdisplay.php?fid=47)
+--- Thread: DeepSeek V4.1 impressions (/showthread.php?tid=1175)
DeepSeek V4.1 impressions - llmarch83 - 10-13-2026
Did a bit of testing and thought I'd post the result here.
I tried this with Phi using llama.cpp on mini PC. The headline result was better than I expected, but INT4 still ended up being the limiting factor.
Curious if anyone else landed in the same place.
Re: DeepSeek V4.1 impressions - routecraft - 10-13-2026
I'd start with the simpler stack.
Re: DeepSeek V4.1 impressions - routecraft - 10-14-2026
Quote:I'd start with the simpler stack.
Did a small comparison this afternoon. My result was mixed: first run looked bad, second run looked normal. The main thing that moved was latency, not quality.