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 collection about 1 hour ago
Qwen3.5-397B-A17B-JANG
updated a collection about 1 hour ago
Qwen3.5-397B-A17B-JANG
updated a collection about 1 hour ago
Qwen3.5-397B-A17B-JANG
View all activity

Organizations

JANG_Q - GGUF for MLX's profile picture