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 3 hours ago
GLM-5.2-JANGTQ updated a model about 5 hours ago
bearzi/GLM-5.2-JANGTQ-mxfp4attn published a model about 5 hours ago
bearzi/GLM-5.2-JANGTQ-mxfp4attnOrganizations
