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 13 hours ago
bearzi/GLM-5.2-JANGTQ updated a model about 15 hours ago
bearzi/GLM-5.2-JANGTQ4 updated a collection about 16 hours ago
GLM-5.2-JANGTQOrganizations
models 54
bearzi/GLM-5.2-JANGTQ
Text Generation • 64B • Updated
bearzi/GLM-5.2-JANGTQ4
Text Generation • 109B • Updated
bearzi/GLM-5.2-JANGTQ_K
Text Generation • 79B • Updated • 6 • 1
bearzi/Kimi-K2.7-Code-JANGTQ_K
Text Generation • 89B • Updated • 889
bearzi/Kimi-K2.7-Code-JANGTQ1
Image-Text-to-Text • 68B • Updated • 11
bearzi/Kimi-K2.7-Code-JANGTQ2
Image-Text-to-Text • 76B • Updated • 12
bearzi/MiMo-V2.5-MLX
Updated • 483
bearzi/MiMo-V2-Flash-JANG_2S
Text Generation • 35B • Updated • 162
bearzi/MiMo-V2-Flash-JANG_2M
Text Generation • 35B • Updated • 122
bearzi/MiMo-V2-Flash-JANG_2L
Text Generation • 35B • Updated • 110