Yohann Bearzi

bearzi

AI & ML interests

Uploading mixed-precision MLX quantizations of popular open-weight models, produced with oMLX’s oQ and JANG on apple silicon. Benchmarks and comparisons are welcome.

Recent Activity

updated a model about 4 hours ago
bearzi/gemma-4-31b-it-oQ8
updated a model about 4 hours ago
bearzi/gemma-4-31b-it-oQ6
new activity about 4 hours ago
bearzi/gemma-4-31b-it-oQ3:Doesn't seem to work.
View all activity

Organizations

JANG_Q - GGUF for MLX's profile picture