Strata is seriously impressive.
I'm now running Qwen 3.8 Flash Next at a bit over 100 tokens a second and the whole box barely hums. Hat's off to Niko1221
Qwen 3.8 flash next (4bit) on halo in pi.
QWEN 3.8 27B prompting LTX 2.5; all running on a Mac Mini M5 Pro 64GB.
The DGX Spark has gone up in price, and that is the bad news.
At a new price of $7000 , alot of people are going to ask - can you do much with just 1 DGX Spark? The good news is you can run more frontier-class stuff on it than ever. 60-70 tok/s (322 in concurrency) on Qwen 3.8
You have reached the end of the archive
All of qwen38