Alex Ziskind
@digitalix
Software engineer making videos about dev gear, local AI, and weird tech experiments
๊ฐ์
March 2009
1.5K ํ๋ก์ ์ค 28.7K ํฌ
What's this? New model gonna need these bad boys. Meta's 816B param Muse Spark is open wieghts ๐คฏ
1M-token context window. And MoE, so likely relatively fast.
Now I'm really curious what my cluster can do!
๋ ๋ณด๊ธฐ
