Run New Llama 3.1 on Your Computer Privately in 10 minutes

25 thoughts on “Run New Llama 3.1 on Your Computer Privately in 10 minutes”

• Check out our updated course on running private AI chatbots on your computer.
  https://bit.ly/skillleap

• "We need to go to an app that a lot of people have never used before…. its called 'Terminal'". OMG that line had me dying!

• Is there a way to bring this local running Llama 3.1 onto my website? I want to share my trained AI with other people. Thanks!

• hugging face llama 3.1 model repo storage is 60 gb but it run very slow for one response and ollama run same llama 3.1model faster but size of llama 3.1 is around 5 gb. what is the difference

• What's so great about running it on your own computer privately etc?! Like what are you able to do that's so great and worth all the trouble? Can you generate AI videos? What?! No body ever explains they just get into all the complex code rigging etc.

• Hi. First of all, thanks for the video. It's really useful and easy to follow step by step. I am running M1 mac air and seems like it's not good enough to run llama 3.1 as it seems to freeze my computer. Which model would you recommend for M1 mac air?

• i do it all but No results found models !

• Those specs for the 405b are not right. I have 64gb's ram and mine flies.with 4080 super and AMD 5900x

• Can we do a APi call of this local LLM in my code ?

• Requirement at 7:56

• docker, ollama also need to run not just installed as u mentioned at 10:21.

• I see chatgpt is becoming the edge of LLM: hey Chatgpt, how do i install this other LLM i want to have?

• this is great, thanks for puting in such simple and understandable way. I can run locally now, is there a way where I can point it out this local models to my python code, or my langchain/llama_index application code?

• Hello thinking about skill.leap. what A.i subscriptions would you recommend?

  For your class?

• does the chatbot have memory??

• does RTX 3050 with 16gb RAM could run 7B model??

• Than you so much. Can you tell me how to acces openAi with WiFi on or off?

• Can we locally remove restraints on LLaMA models, including ethical safeguards?
  Thanks

• still confused on github … it didnt take me there so i dont have a clue as to where your at there

• Are there way to select hard drive when install?

  My C Drive is almost full, how can I select my other drive?

• You have great teaching skills. Thank you for making it so simple!

• Would like to learn to do Llama + Groq + iPhone shortcuts to run llama.

• Thank You for this informative and timely vid. I have been testing 'Ollama' llama3.1:8b for my Python RAG dev and it runs surprisingly well. I use both the Flask and 'Gradio' GUI. Unfortunately, I CANNOT recommend using WebUI since it's docs clearly state: "DANGER: Admin Creation: The first account created on Open WebUI gains Administrator privileges, controlling user management and system settings.
  
  " The implication is that WebUI via docker gains Admin privileges to your OS and your computer. This is too much of HIGH RISK!

• thanks a lot. That's what i wanted to do. Now i can upload files and not pay for chatgpt plus. But anyway, it is very slow and uses a lot of cpu. Do you know any tweaks where i can share the workload with the gpu?

• Too many steps just for a ui. try LM studio or gpt4all. If you want to use documents you can use gpt4all. But still you can just copy paste a whole document in any of them if the models can handle that many tokens and usually they do.

Comments are closed.