Inference › Harnesses, Agents & Orchestration › Workflows / Automation v
DeepSeek V4.1 impressions

Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Linear Mode
DeepSeek V4.1 impressions
rocmhouse90 Offline
Member
***
Posts: 63
Threads: 1
Joined: Sep 2026
Reputation: 0
#10
10-15-2026, 10:09 PM
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.
still benchmarking everything
Find
Reply


Messages In This Thread
DeepSeek V4.1 impressions - by routecraft - 10-05-2026, 05:43 AM
Re: DeepSeek V4.1 impressions - by routecraft - 10-06-2026, 05:57 PM
Re: DeepSeek V4.1 impressions - by edgecoast - 10-08-2026, 06:17 AM
Re: DeepSeek V4.1 impressions - by batchpeak - 10-09-2026, 06:29 AM
Re: DeepSeek V4.1 impressions - by latentpeak22 - 10-13-2026, 09:16 AM
Re: DeepSeek V4.1 impressions - by routecraft - 10-09-2026, 07:10 AM
Re: DeepSeek V4.1 impressions - by tensorport - 10-10-2026, 07:38 AM
Re: DeepSeek V4.1 impressions - by routecraft - 10-10-2026, 08:47 AM
Re: DeepSeek V4.1 impressions - by routecraft - 10-14-2026, 09:53 AM
Re: DeepSeek V4.1 impressions - by rocmhouse90 - 10-15-2026, 10:09 PM
Re: DeepSeek V4.1 impressions - by routecraft - 10-19-2026, 01:49 AM
Re: DeepSeek V4.1 impressions - by routecraft - 10-15-2026, 11:13 PM
Re: DeepSeek V4.1 impressions - by mangoquill - 10-15-2026, 11:53 PM
Re: DeepSeek V4.1 impressions - by routecraft - 10-16-2026, 12:46 AM
Re: DeepSeek V4.1 impressions - by routearch - 10-19-2026, 12:55 AM

Forum Jump:


Users browsing this thread: 1 Guest(s)