alt Hacker NewsFlash[1]: 309B total / 15B activated parameters
Pro [2]:, 1.02T total / 42B activated parameters
Replies
verdverm • today at 8:46 PM
curious why the HF pill (on the right) always has inaccurate values
➕ show 1 reply
segmondy • today at 9:23 PM
more like 500B in FP8
There's also a Qwen 3.5 9B distill
https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B