GPT4ALL on AMD 6800u - Speed & answer comparison - mpt vs. gpt4all - 7b vs. 13b [Linix]
This is my second video running GPT4ALL on the GPD Win Max 2.
This time I do a short live demo of different models, so you can compare the execution speed and output quality of those models.
It is only a short test, as it is sufficient to demonstrate execution speed.
Output quality varies a lot depending on model, prompt and question. Also new models will come frequently, so the results would be outdated very soon anyways.
GPT4ALL in an easy to install AI based chat bot.
It works on Windows and Linux.
In this demo, we are running Linux. For Windows, see my other Video.
------------
Links:
GPT4ALL website: https://gpt4all.io/index.html
GPT4ALL Git: https://github.com/nomic-ai/gpt4all
GPT4ALL Discord: https://discord.gg/MexcSdVytv
Interview with founder: https://github.com/nomic-ai/gpt4all
Help me and subscribe: https://www.youtube.com/channel/UCjLMAxvG4CxOqVfai_JhnLQ?sub_confirmation=1
------------
Timestamps:
00:00 - Introduction
00:56 - Overview of the models in this comparison
02:30 - Question 1: Psychology (Post Error Slowing)
04:37 - Question 2: Story about Mage & Knight
07:12 - Question 3: Programming, C++ - Raw pointer vs. Smart pointer
09:46 - conclusion & personal opinion