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 about 11 hours ago
MiniMax-M2.7-JANG updated a collection about 11 hours ago
MiniMax-M2.7-JANG updated a collection about 11 hours ago
MiniMax-M2.7-JANGOrganizations
models 143
bearzi/MiniMax-M2.7-JANG_6M
Text Generation • 47B • Updated
bearzi/MiniMax-M2.7-JANG_4S
Text Generation • 32B • Updated
bearzi/MiniMax-M2.7-JANG_4M
Text Generation • 33B • Updated
bearzi/MiniMax-M2.7-JANG_4L
Text Generation • 33B • Updated
bearzi/MiniMax-M2.7-JANG_3S
Text Generation • 25B • Updated
bearzi/MiniMax-M2.7-JANG_3M
Text Generation • 26B • Updated
bearzi/MiniMax-M2.7-JANG_3L
Text Generation • 26B • Updated
bearzi/MiniMax-M2.7-JANG_2S
Text Generation • 18B • Updated
bearzi/MiniMax-M2.7-JANG_2M
Text Generation • 19B • Updated
bearzi/MiniMax-M2.7-JANG_2L
Text Generation • 19B • Updated