dr_cintas
Region: US
Sunday 01 November 2026 14:59:12 GMT
17319
934
10
122
Music
Download
Comments
The Inference AI :
Mesh LLM stood out to me, because splitting a 70B model across computers people already own changes who can actually run serious models at home. Opera running open models inside the browser points the same way, toward local control instead of always renting cloud access. As a Latino creator, I care about this because local models lower the cost barrier for people who cannot rent big cloud setups. I am curious which approach holds up better for long sessions, a split model or a browser model?
2026-11-01 20:54:52
0
Not Real Earth :
5090 cpu?😳
2026-11-01 17:56:56
1
SMAVOTEX :
cool
2026-11-01 20:31:45
0
AI Compare Ninja :
un recap, which story from this week do you think actually matters most for regular users?
2026-11-02 13:02:05
0
𝓐𝓷𝓭𝓻𝓮𝔀 :
yall need to check this out free ai https://github.com/brittanykemp160-rgb/solace
2026-11-02 05:17:53
0
sunsetzs5 :
lowkey the best free ai rn https://github.com/brittanykemp160-rgb/solace
2026-11-02 06:07:28
0
dingdongpeng :
Chinas AI bubble just blow up
2026-11-01 15:20:15
0
kil :
😁😁😁
2026-11-02 01:54:52
0
To see more videos from user @dr_cintas, please go to the Tikwm
homepage.
