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 1 day ago
GLM-5.2-JANGTQ updated a model 1 day ago
bearzi/GLM-5.2-JANGTQ-mxfp4attn published a model 1 day ago
bearzi/GLM-5.2-JANGTQ-mxfp4attnOrganizations
models 56
bearzi/GLM-5.2-JANGTQ-mxfp4attn
Text Generation • 66B • Updated • 17
bearzi/GLM-5.2-JANGTQ_K-mxfp4attn
Text Generation • 65B • Updated • 39
bearzi/GLM-5.2-JANGTQ
Text Generation • 64B • Updated • 1.53k • 3
bearzi/GLM-5.2-JANGTQ4
Text Generation • 109B • Updated • 1.18k • 1
bearzi/GLM-5.2-JANGTQ_K
Text Generation • 79B • Updated • 2.4k • 3
bearzi/Kimi-K2.7-Code-JANGTQ_K
Text Generation • 89B • Updated • 1.03k • 1
bearzi/Kimi-K2.7-Code-JANGTQ1
Image-Text-to-Text • 68B • Updated • 24
bearzi/Kimi-K2.7-Code-JANGTQ2
Image-Text-to-Text • 76B • Updated • 15
bearzi/MiMo-V2.5-MLX
Updated • 193
bearzi/MiMo-V2-Flash-JANG_2S
Text Generation • 35B • Updated • 28
datasets 0
None public yet