logoalt Hacker News

slikenyesterday at 4:16 PM1 replyview on HN

> You won't like it, but the answer is Apple.

Or strix halo.

Seems rather over simplified.

The different levels of quants, for Qwen3.6 it's 10GB to 38.5GB.

Qwen supports a context length of 262,144 natively, but can be extended to 1,010,000 and of course the context length can always be shortened.

Just use one of the calculators and you'll get much more useful number.


Replies

3836293648yesterday at 9:10 PM

What Strix Halo system has unified memory? A quick google says it's just a static vram allocation in ram, not that CPU and GPU can actively share memory at runtime