Since this has no dedicated GPU, I'm not sure if 16 GB RAM will be enough to fit even the Gpt-Oss-20B LLM, because out of the 16 GB RAM, 4 GB, or more, will be required by the OS itself.
To run the LLM, download llama.cpp (it has a new and in active development webUI) and the LLM at e.g. huggingface.co/unsloth/gpt-oss-20b-GGUF (Q8 or F16 are recommended and Q4_K_M is the minimum recommended quant).
PS: gpt-oss-20b is by the ChatGPT makers, has 7.4 million downloads per month and you have never heard of it? Original source: huggingface.co/openai/gpt-oss-20b
And if you thought you could upgrade the RAM, nope, it's
soldered. 16 GB RAM are going to age like milk. Even on Steam 32 GB RAM will soon overtake 16 GB RAM (see the monthly Steam Hardware Survey and news about the overtake). 24 GB RAM should be the new 16 GB RAM.
But for 660 bucks, I guess the 16 GB RAM are unfortunately expected in the current time.
At least the display is 16:10 and it's better than 16:9.
But 57.7% sRGB coverage does not even cover the ancient sRGB web standard:
Quote from: en.wikipedia.org/wiki/SRGBsRGB (standard RGB) is a color space, for use on monitors, printers, and the World Wide Web. It was initially proposed by HP and Microsoft in 1996[2] and became an official standard of the International Electrotechnical Commission (IEC) as IEC 61966-2-1:1999.[1] It is the current standard colorspace for the web, and it is usually the assumed colorspace for images that do not have an embedded color profile.
Deutsch
English
Español
Français
Italiano
Nederlands
Polski
Português
Русский
Türkçe
Svenska
Chinese
Magyar