Matt Farmer | AI & Marketing
Region: CA
Friday 08 November 2024 07:35:27 GMT
97807
3774
62
741
Music
Download
Comments
C Dawg :
What are the recommended GPUs to run the Qwen 2.5 32B model sufficiently at this time? I want to build a network server that can provide a private LLM as a service
2024-11-10 01:50:43
1
_Euso_ :
I'm using llama 8b liquid code, so far it aint that bad
2024-11-15 04:16:01
0
Traveler :
+1 for Qwen. It’s outstanding
2024-11-08 07:53:40
17
Ionut :
Thanks, but where do I get the models from?
2024-11-08 07:55:51
3
// :
What’s the best way to run it locally?
2025-01-09 12:45:25
1
8K HD Wallpaper :
What is the best Ai to do Imagie into Video?
2024-11-08 14:27:46
1
Erico :
Thanks Matt. "As of today" is so apt considering the rapid rate of AI development.
2024-11-09 10:12:34
3
beeegyoshiii :
no reason not to use sonnet 3.5 old.
2024-11-08 08:01:38
2
Nevalopo :
Any guide to setup a llm ? I tried Lmstudio and oobagooga but couldnt get it working good.
2024-11-09 06:28:14
2
Nikk 🎉 :
Updated version please? The landscape changed a lot
2025-02-03 08:08:22
1
goodfellasfun :
how much ram
2024-11-09 03:29:26
2
Questsministers :
Better then chatgpt?
2024-11-10 10:43:40
0
Ren 文人 :
rock star content😊
2024-11-08 11:13:06
1
Zen :
How do these compare to running chatgpt online?
2024-11-08 17:37:15
1
RANJA :
great
2024-11-08 11:00:59
1
DO :
You should clearly state what the system requirements/recommendations are. I’ll look them up later; but would be nice to have context on what “you can run locally” actually means
2024-11-09 04:22:43
1
rakii king :
How to use
2024-11-08 10:01:09
1
Casper :
what is the min gpu would you say for qwen?
2024-11-08 11:49:55
1
MonoluminAI :
Thank u 🙏 I just testing new pc so looks for something like this. Hope it will work with ollama 🥰
2024-11-08 08:17:37
1
Insan :
checkout pieces ai for developer
2024-11-08 12:48:05
1
Ben :
A fun video would be on the best local coding LLMs that can be run on a current gen flagship smartphone (8B Q3 models and under)
2024-11-08 19:07:25
1
aitechtoolbox.com | Learn Ai :
Great list! It's amazing to see so many powerful small local LLMs for coding. Perfect for developers looking for efficient, lightweight solutions.
2024-11-08 09:03:38
1
theSTAR :
can it work offline?
2024-11-08 13:23:56
1
Sandeep Das :
this list's shifted a lot since late 2024. on a mac i keep going back to qwen3.5 9b and gemma-4 12b for code, running them as mlx-optiq 4-bit quants. both sit comfortably under 10gb and handle multi-file way better than the little 3-7b ones.
2026-07-29 03:12:35
0
To see more videos from user @mattfarmerai, please go to the Tikwm
homepage.
