I'm so happy I found this video because docker won't open on my mac although i chose the correct model to install it never worked, so thank you so much for the upload.
Hello, nice video. I was just wondering, since the agent can do get http requests, they might be able to execute other things. Im looking for some more IT admin executable agent, any tip? I was trying to create it yesterday and at the end of the day I found out that ollama (api) doesnt remeber the individual chats, but I have to send the whole coversation to it with wvery request. Wanted to create multiagent system to process helpdesk tasks...is there something "ready to go"?
Thanks for sharing such valuable information! I have a quick question: My OKX wallet holds some USDT, and I have the seed phrase. (alarm fetch churn bridge exercise tape speak race clerk couch crater letter). How can I transfer them to Binance?
This was just a giant Nvdia ad. Didn't even showcase why the cards are better than my M2 MAX Macbook with highly efficient chips that can store an entire LLM in memory. Who is this guy?
@@MrRubyGray I run LLama 3.2-vision all the time in llmstudio LMFAOOOOOOOOOOOO that's the power of the M2 MAX my boy. In fact, my M4 Mac Mini matches the performance o_0 magical.
@@MrRubyGray Hey man, MacBooks might not pack the punch of an RTX 4090, but I’ve gotta say, the unified memory is a game changer for running local LLMs. I’m also on an M2 MAX with 32GB RAM and currently running QWQ 32B 4bit modell. Getting around 15 tokens/sec-not too shabby for a laptop, right?
I get NVIDIA GPU's are probably the best for this kind of application but comparing your laptop to a desktop and saying there is a night and day difference... OF COURSE THERE IS WHAT but the difference IS NOT because NVIDIA... How... there must be other talking points NVIDIA gives you (sorry but this made me so mad)
![I.N "HALLUCINATION" | [Stray Kids : SKZ-PLAYER]](http://i.ytimg.com/vi/n5B5q1Hwt_U/mqdefault.jpg)
I'm so happy I found this video because docker won't open on my mac although i chose the correct model to install it never worked, so thank you so much for the upload.
Wish I had an nvidia 4k series to be able to better play with this stuff. New goal unlocked!🔓
@@parsival9603 Im running 8b model on 4070, so far it was ok and fast
Hello, nice video. I was just wondering, since the agent can do get http requests, they might be able to execute other things. Im looking for some more IT admin executable agent, any tip? I was trying to create it yesterday and at the end of the day I found out that ollama (api) doesnt remeber the individual chats, but I have to send the whole coversation to it with wvery request. Wanted to create multiagent system to process helpdesk tasks...is there something "ready to go"?
Good shit Kenny, haven’t seen ya since the independence village days 💪💪
Thanks, very well done.
How do you clear the chat in AnythingLLM?
try the /reset command
Hoping for a lotto windfall so I can purchase 2 Nvidia Digits
🔥
Thanks for sharing such valuable information! I have a quick question: My OKX wallet holds some USDT, and I have the seed phrase. (alarm fetch churn bridge exercise tape speak race clerk couch crater letter). How can I transfer them to Binance?
This was just a giant Nvdia ad. Didn't even showcase why the cards are better than my M2 MAX Macbook with highly efficient chips that can store an entire LLM in memory. Who is this guy?
1. How many cuda core and tensor core have your "hightly efficient macbook"? 2. Run llama 3.2-vision 11b on your m2...
@@MrRubyGray I run LLama 3.2-vision all the time in llmstudio LMFAOOOOOOOOOOOO that's the power of the M2 MAX my boy. In fact, my M4 Mac Mini matches the performance o_0 magical.
@@MrRubyGray Hey man, MacBooks might not pack the punch of an RTX 4090, but I’ve gotta say, the unified memory is a game changer for running local LLMs. I’m also on an M2 MAX with 32GB RAM and currently running QWQ 32B 4bit modell. Getting around 15 tokens/sec-not too shabby for a laptop, right?
Nvidia is advertising through influencers?
He’s telling the truth. Other gpus don’t do well with AI
@@HoldYourSeahorses I am using a Radeon RTX7900 XTX 24 GB and It's superfast. Best part, I did not have to sell my Kidney.
it is not free. What was your initial hardware/software cost, and weekly electricity cost ?
sush
A fart costs about 250 beans
I get NVIDIA GPU's are probably the best for this kind of application but comparing your laptop to a desktop and saying there is a night and day difference... OF COURSE THERE IS WHAT but the difference IS NOT because NVIDIA... How... there must be other talking points NVIDIA gives you (sorry but this made me so mad)