Ollama on CPU and Private AI models!

This Ollama Crash Course introduces you
1. Ollama Intro
2. Ollama Run Local LLMs
3. Local LLMs as API End points
4. Local LLMs with Characters
5. Local LLMs with GGUF

❤️ If you want to support the channel ❤️
Support here:

🧭 Follow me on 🧭

[davidlepold]

it works! :) - installed llama2 and mistral on Debian, even without GPU for shorter prompts. Thanx a lot.

[JimMendenhall]

Thanks for another great video. I love how you couldn't just exit the program without thanking the LLM and assuring it that you're okay. Love it!

[MuthukumarKB]

another awesome video.. I am liking all of your videos. The way you explain is awesome.. pls keep up the good work!

[sanjay]

the era of portable LLM's is here

[nathanbanks]

Now I've gotta try this. I've been impressed by text-generation-webui, so I never got around to trying other interfaces. This definitely looks better for some use cases.

[a_LEGION]

After watching your video, I have utilized Ollama in a Windows environment that has an i5 processor and 12 GB of RAM, and it is running decently. I have employed Docker for this purpose.

[cscarpa]

Great video, as always! It would be nice to see a use case of RAG system based on Ollama and Llamaindex.

[mariuszkreft]

You can do ollama on windrows with WSL2

[ArtisanTony]

I gladly give up conveniences to avoid macs lol

[JohnMcclaned]

can llm's run doom though? if not, im not interested.

[izzyblast]

Hey thank you for the video. I want to say that all those critiques of yourself me and everyone else watching aren't thinking. We love your content and vibe so keep going bro and don't be so harsh on yourself.

[dkracingfan]

The github now shows Widows is coming soon!

[ghostwhowalks]

What would be the disadvantages of running ollama ? Is it possible for you to do a comparison of models ? How deep does OpenAI's moat run given that opensource is innovating at a faster rate ?

[tech]

i wish there was an open source llm optimized for interacting with autogen!

[Aarifshah-A]

Windows users can use WSL easy peasy for techy people ...

[ojikutu]

Thanks. Can you show how to finetune mistral 7b on your own system with 3090?

[mimotron]

For Windows user, can't you achieve the same thing with Pinokio ?

[hp]

Great video! Could you please make a video about how to use new OpenAI TTS via a google colab or any other easy way? Help appreciated.

[mustafabasrai]

Please show for windows as well if possible

[vivekpadman]

How can someone with a windows machine and without a gpu get a llm running as a api. Can you make a video of how to do it in colab or some easy to use cloud server?