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 20 hours ago
bearzi/MiMo-V2.5-MLX published a model 10 days ago
bearzi/MiMo-V2.5-MLX updated a collection 28 days ago
MiMo-V2-Flash-JANGOrganizations
models 151
bearzi/MiMo-V2.5-MLX
Updated • 325
bearzi/MiMo-V2-Flash-JANG_2S
Text Generation • 35B • Updated • 309
bearzi/MiMo-V2-Flash-JANG_2M
Text Generation • 35B • Updated • 191
bearzi/MiMo-V2-Flash-JANG_2L
Text Generation • 35B • Updated • 168
bearzi/MiMo-V2-Flash-JANG_1L
Text Generation • 35B • Updated • 136
bearzi/Qwen3.5-397B-A17B-JANG_3M
53B • Updated • 6
bearzi/Qwen3.5-397B-A17B-JANG_3S
53B • Updated • 6
bearzi/Qwen3.5-397B-A17B-JANG_2L
54B • Updated • 7 • 1
bearzi/Qwen3.5-397B-A17B-JANG_2M
53B • Updated • 7 • 1
bearzi/Qwen3.5-397B-A17B-JANG_6M
83B • Updated • 7