Ivan from a Tech Room
Region: DE
Sunday 15 November 2026 15:18:10 GMT
8791
406
17
26
Music
Download
Comments
_Sleeper_ :
Best local model for dev please? GPU only has 8GB NVRam
2026-11-15 15:33:09
2
Георги Чавдаров :
What is the best for 16 vram and 64 ram
2026-11-15 19:21:10
0
alex123ен :
gemma 4
2026-11-15 21:12:45
0
أورانوس :
I like qwen. but still i think local models not good enough
2026-11-15 18:24:51
2
Nid | NP :
the better question is what was the model trained on/for ? but sadly very few models are open source. so you kind of got to take their word or some random guy's opinion for it. Wastes some time.
2026-11-15 15:39:07
1
cayvotmuoi69 :
I’m using Swift 1.5 from Strata on github. Great experience, their models can offload 🥳
2026-11-15 18:54:14
0
Morgan la Fey :
128Gb of VRAM is the best local model 👍
2026-11-15 15:48:19
0
Abdulrahman Sa :
when they ask this they probably mean local LLM for chatting
2026-11-15 15:53:22
0
Leo Bennett | Phone & AI :
And we shouldn’t forget that the list will change with time
2026-11-15 17:12:58
0
tik_tok_shau :
just use benchmarks
2026-11-15 16:34:35
0
Beans :
Depends on what u want to do w it.
2026-11-15 18:20:18
0
Thor :
Why is it slow?
2026-11-15 15:25:03
0
To see more videos from user @easybits.tech.room, please go to the Tikwm
homepage.
