Llama 3.3 – better than ChatGPT, runs locally, 100% private

Subscribe if you're serious about AI.

Learn how to use Llama 3.3 and run it on your phone.

[thinkgenerative]

That app seems very helpful. Escpecially considering that someday soon >10B parameter models may become much more capable than they are today.

[DanielDota]

You forgot to mention that the model is 45 gb which doesnt even fit on the post expensive customer gpu, meaning it will offload to ram and be incredibly slow. So you have to use quantized version which isnt better than gpt 4o, and you still need a very good computer for it.

[asirush]

Though you're gonna run llm on a phone, but its just using api🗿

[Centaurman]

Would you do a video on how to get an open source “advanced voice mode” working on our phones? 🙏

[marcusk]

Just waiting to the uncensored version.

[MJFUYT]

Excellent commentary and content David. Thanks for sharing your knowledge!

[saltygamer]

What are the computer specs needed to run llama 3.3 locally?

[nickdanylchuk]

Great instructions. Please make the video with SSL in the API. Thank you.

[dk-pzxv]

requesting a tutorial for the latest tech ai image generation as well! :)

[KrzysztofKuczek]

Hi, thanks for your guide. Stupid question, what is the reason, the AnythingLLMDesktop + mistrall produces different output then, mistrall run directly using ollama? When i use ollama, i can comunicate with it using different then English language, but using anything llm it's not possible, it can translate, but seems to be forced to communicated in non English languages. Perhaps some settings of context or promp. Do you know how to fix it ? Thank u in advance.

[constantintaivan]

Hey David, I enjoyed wathching the video; btw is there any way to limit the RAM memory used? I got this for llama3.3: model requires more system memory (44.8 GiB) than is available (31.0 GiB), thanks

[naeemulhoque]

Is there a good vision language model that is also uncensored?
llama3.2 vison is extremely censored.

[cabg]

Can this realistically run on a Macbook M4 Max? Or will it crawl?

[originalmagneto]

Hey Ondrej, iPhone Mirroring exists 😬 Is it possible to record the screen while iPhone Mirroring? Maybe a better setup, no?

[BladeReader]

What version have you downloaded ?? Mac os / linux / windows?
Regards

[itzmehosama]

What are the specs needed? It says for me not enough memory

[igalgerman]

Hi
is there android app for connecting to the local ai?

[simongentry]

David - which macbook r u using? i'm on the macbook pro max1

[StrixTechnica]

so *why* is ollama 3.3 better than chatgpt?

[sevenedus]

Someone has to say - it is reasonably open source not completely.