sadie.ontech
Region: PT
Friday 11 September 2026 21:07:01 GMT
214994
8616
178
3420
Music
Download
Comments
raffert :
what kind of hardware do you need for something like this?
2026-09-29 20:13:08
2
Gajda Cristian :
you can run it locally, no API.... how to install, enter API key fun
2026-09-12 00:06:14
67
1 million people :
You don’t pay for api too. Just run it locally and connect your “api key”🤣🤣🤣
2026-10-15 01:59:47
136
SonicVisual :
I'm tired of all these new tech reorts every second. Can't you guys come up with the One-Ultimate-Software that is capable of doing everything and only than inform us about it.
2026-10-16 11:45:43
14
angr_man :
no one can beat anthropic Claude in coding
2026-09-30 07:55:21
21
phoenixriver :
200GB RAM ?
2026-09-29 17:02:17
9
Art6us :
I've tested it for coding and it sucks compared to gpt 6 sol and terra
2026-09-28 15:38:37
5
preadyt8 :
how much RAM is required locally
2026-09-12 15:37:14
3
ToBeHonest :
Glm from z.ai no u can't run it locally and glm5. 3 has already been released, the glm family also has other types of models image to text as example as well as a flash
2026-11-02 20:00:26
0
Kudzai N1th :
no claude is still on top fpr image generation is too far behind
2026-10-22 11:43:02
0
Jakeyyx :
Not even close to claude
2026-09-12 05:52:14
7
SuperUser47 :
"one zero time... ". This A.I is dumb it can't say "ten times" 😭😭
2026-09-12 20:02:11
10
Volta.Quest :
BS. You need a huge amount of vRAM to run it. Impossible. I deploy LLMs fir a living.
2026-09-13 04:24:47
17
. :
I am stupid.. and do not know much about ai. But what is the difference with chat gpt?
2026-10-01 05:18:25
0
crankitup21 :
I am currently using GLM 5.2 via Ollama cloud with Claude Code and it is working pretty well. Fundamentally less expensive than e.g. Opus 5
2026-09-29 20:00:18
5
Gorka :
in your computer HAHAHAHAHA might need 8xA100 or more 😭 still great to have open weight models tho
2026-09-30 14:38:57
6
Hum Dev :
connect your API key 😂
2026-10-29 06:30:41
2
Mark Sowden :
If it wasn't the "One Zero times" rather than 10 times I wouldn't have realised this was AI too.
2026-09-12 01:21:34
10
Blank :
In GLM 5.2, it has been out for months; GLM 5.3 arrived a month ago.
2026-09-30 00:11:29
18
HouseKonnect :
we are on glm 5.3 and glm5.3 flash
2026-09-24 20:08:42
7
Robert Gjergji :
This AI video
2026-10-11 17:07:38
1
LoveThisWorld :
is this it? can you confirm please?
2026-11-01 06:52:10
1
Luca Bianconi :
How can it be local if i need a api
2026-10-16 12:26:50
0
Nik Niksen :
For what do you need an api key it it’s running locally?
2026-09-12 13:34:33
4
pt :
how much vram is necessary for this?
2026-10-16 22:43:44
0
To see more videos from user @sadie.ontech, please go to the Tikwm
homepage.
