+- 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=1207)
Pages:
1
2
DeepSeek V4.1 impressions - routecraft - 10-14-2026
Wanted to compare notes with people doing similar things.
I'm trying to decide whether to keep the current stack or change course. Main question is how people here are handling reranking.
If you've tested something similar, what did you keep and what did you stop bothering with?
Re: DeepSeek V4.1 impressions - routecraft - 10-15-2026
same here on my side.
Re: DeepSeek V4.1 impressions - batchpeak - 10-18-2026
A couple things I'd check first. Before rebuilding anything, I'd test one clean baseline with Phi and compare from there. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
Re: DeepSeek V4.1 impressions - routecraft - 10-18-2026
Need a little more detail here. Are you testing this on 7900 XTX or something else?
Re: DeepSeek V4.1 impressions - prompttinker44 - 10-18-2026
Need a little more detail here. Is this local-only or are you routing anything externally?
Re: DeepSeek V4.1 impressions - thetarunner - 10-18-2026
Maybe, but I had the opposite result. I get why that seems right, but on Threadripper box the bottleneck felt elsewhere. Worth testing the simpler explanation before adopting the more interesting one.
There are a few different conversations hiding inside this thread, so being explicit about the goal helps.
Re: DeepSeek V4.1 impressions - routecraft - 10-18-2026
I'd start with the simpler stack.
Re: DeepSeek V4.1 impressions - plainember52 - 10-18-2026
What worked for me was pretty simple. Before rebuilding anything, I'd test one clean baseline with Mistral and compare from there. Once you know the plain path works, then add the faster path back in piece by piece.
Re: DeepSeek V4.1 impressions - mellowwire98 - 10-18-2026
Good point. I ended up in about the same place using PyTorch.
Re: DeepSeek V4.1 impressions - routecraft - 10-18-2026
What worked for me was pretty simple. Before rebuilding anything, I'd test one clean baseline with Phi and compare from there. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.