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 2 days ago
Deepseek-4.1-Flash-1007-oQe updated a model 2 days ago
bearzi/DeepSeek-V4.1-Flash-1017-abliterated-oQ4e-mtp published a model 2 days ago
bearzi/DeepSeek-V4.1-Flash-1017-abliterated-oQ4e-mtpOrganizations
models 56
bearzi/DeepSeek-V4.1-Flash-1017-abliterated-oQ4e-mtp
Image-Text-to-Text • 129B • Updated • 196
bearzi/DeepSeek-V4.1-Flash-1017-oQ4e-mtp
Image-Text-to-Text • 129B • Updated • 351
bearzi/GLM-5.2-JANGTQ
Text Generation • 64B • Updated • 138 • 3
bearzi/GLM-5.2-JANGTQ4
Text Generation • 109B • Updated • 66 • 1
bearzi/GLM-5.2-JANGTQ_K
Text Generation • 79B • Updated • 156 • 3
bearzi/Kimi-K2.7-Code-JANGTQ_K
Text Generation • 97B • Updated • 148 • 1
bearzi/Kimi-K2.7-Code-JANGTQ1
Image-Text-to-Text • 68B • Updated • 13
bearzi/Kimi-K2.7-Code-JANGTQ2
Image-Text-to-Text • 76B • Updated • 12
bearzi/MiMo-V2.5-MLX
Updated • 49
bearzi/MiMo-V2-Flash-JANG_2S
Text Generation • 474B • Updated • 19
datasets 0
None public yet