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 9 hours ago
bearzi/Kimi-K2.7-Code-JANGTQ_K updated a collection about 9 hours ago
Kimi-K2.7-Code-JANGTQ updated a collection about 9 hours ago
Kimi-K2.7-Code-JANGTQOrganizations
models 51
bearzi/Kimi-K2.7-Code-JANGTQ_K
Text Generation • 89B • Updated
bearzi/Kimi-K2.7-Code-JANGTQ1
Image-Text-to-Text • 68B • Updated
bearzi/Kimi-K2.7-Code-JANGTQ2
Image-Text-to-Text • 76B • Updated
bearzi/MiMo-V2.5-MLX
Updated • 248
bearzi/MiMo-V2-Flash-JANG_2S
Text Generation • 35B • Updated • 189
bearzi/MiMo-V2-Flash-JANG_2M
Text Generation • 35B • Updated • 119
bearzi/MiMo-V2-Flash-JANG_2L
Text Generation • 35B • Updated • 113
bearzi/MiMo-V2-Flash-JANG_1L
Text Generation • 35B • Updated • 101
bearzi/MiniMax-M2.7-JANG_4M
Text Generation • 33B • Updated • 107
bearzi/MiniMax-M2.7-JANG_4L
Text Generation • 33B • Updated • 102