+- 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=745)
Pages:
1
2
DeepSeek V4.1 impressions - routecraft - 10-05-2026
This keeps coming up in conversation so I figured I'd start a thread.
The more I work with local setups, the more it seems like tokens/sec decides everything downstream.
Maybe obvious to some of you, but it clicked for me this week.
My use case is pretty ordinary: local chat, some document work, and occasional batch jobs.
Re: DeepSeek V4.1 impressions - routecraft - 10-06-2026
My first guess would be this: On 5090, the easiest win is often to back off the aggressive settings and see whether the problem survives. Once you know the plain path works, then add the faster path back in piece by piece.
Re: DeepSeek V4.1 impressions - edgecoast - 10-08-2026
Ran a quick check on my box. I couldn't reproduce the slowdown until I pushed context much higher. The main thing that moved was latency, not quality.
Re: DeepSeek V4.1 impressions - batchpeak - 10-09-2026
Quote:Ran a quick check on my box. I couldn't reproduce the slowdown until I pushed context much higher. The main thing that moved was latency, not quality.
Did a small comparison this afternoon. The issue went away once I changed one setting and restarted the stack cleanly. The surprise was that memory pressure showed up before throughput collapsed.
Re: DeepSeek V4.1 impressions - routecraft - 10-09-2026
A couple things I'd check first. If you're on MLX, I'd confirm the version first and then reduce variables until the behavior is obvious. Not glamorous advice, but repeatable baselines save a lot of time.
Re: DeepSeek V4.1 impressions - tensorport - 10-10-2026
Good point. The pattern around tool calling has been pretty similar for me.
Re: DeepSeek V4.1 impressions - routecraft - 10-10-2026
Quote:Good point. The pattern around tool calling has been pretty similar for me.
What worked for me was pretty simple. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at MoE serving. Not glamorous advice, but repeatable baselines save a lot of time.
Re: DeepSeek V4.1 impressions - latentpeak22 - 10-13-2026
A couple things I'd check first. On B200, the easiest win is often to back off the aggressive settings and see whether the problem survives.
Re: DeepSeek V4.1 impressions - routecraft - 10-14-2026
Ran a quick check on my box. The issue went away once I changed one setting and restarted the stack cleanly. I expected the model choice to matter more than it did.
Re: DeepSeek V4.1 impressions - rocmhouse90 - 10-15-2026
Did a small comparison this afternoon. I couldn't reproduce the slowdown until I pushed context much higher. I expected the model choice to matter more than it did.