GRIN-MoE
General purpose
A new MoE model series from Microsoft. It has some architecture tweaks, such as SparseMixer-v2, but it isn't clear what the differentiator is (like Phi).
Adoption · Hugging Face
RAM score
—
Hugging Face Downloads
308
last 30d
74.8K
all time
HF Likes
201
Relative Adoption Metric contextualizes downloads against the model's size bucket.
Related Models