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
routecraft Offline
Member
***
Posts: 193
Threads: 27
Joined: Aug 2026
Reputation: 0
#12
10-09-2026, 09:48 PM
Quote:[quote]Appreciate the detail. That matches what I saw on mini PC. The biggest change for me was simplifying the stack instead of adding one more optim

I tested this tonight. My result was mixed: first run looked bad, second run looked normal. The surprise was that memory pressure showed up before throughput collapsed.
routing beats arguing over one perfect model
Find
Reply


Messages In This Thread
DeepSeek V4.1 impressions - by rocmriley - 09-28-2026, 09:32 AM
Re: DeepSeek V4.1 impressions - by fastquill74 - 09-29-2026, 09:49 PM
Re: DeepSeek V4.1 impressions - by routecraft - 09-30-2026, 12:08 AM
Re: DeepSeek V4.1 impressions - by quantghost - 10-03-2026, 12:18 AM
Re: DeepSeek V4.1 impressions - by routecraft - 10-03-2026, 08:51 AM
Re: DeepSeek V4.1 impressions - by oxiderunner - 10-06-2026, 09:35 AM
Re: DeepSeek V4.1 impressions - by routecraft - 10-06-2026, 11:19 AM
Re: DeepSeek V4.1 impressions - by promptpoint - 10-06-2026, 03:43 PM
Re: DeepSeek V4.1 impressions - by routecraft - 10-06-2026, 04:57 PM
Re: DeepSeek V4.1 impressions - by routecraft - 10-09-2026, 05:03 PM
Re: DeepSeek V4.1 impressions - by relayforge - 10-09-2026, 09:31 PM
Re: DeepSeek V4.1 impressions - by routecraft - 10-09-2026, 09:48 PM
Re: DeepSeek V4.1 impressions - by quantyard - 10-10-2026, 09:52 PM
Re: DeepSeek V4.1 impressions - by routecraft - 10-13-2026, 10:00 PM
Re: DeepSeek V4.1 impressions - by routecraft - 10-13-2026, 10:35 PM

Forum Jump:


Users browsing this thread: 1 Guest(s)