bearzi/Qwen-3.6-27B-JANG_4M
Text Generation • 31B • Updated • 15
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.
Organizations
bearzi/Qwen-3.6-27B-JANG_4L
Text Generation • 33B • Updated • 24 • 1
bearzi/Qwen-3.6-27B-JANG_4K
Text Generation • 37B • Updated • 11
bearzi/Qwen-3.6-27B-JANG_3S
Text Generation • 31B • Updated • 18
bearzi/Qwen-3.6-27B-JANG_3M
Text Generation • 33B • Updated • 23
bearzi/Qwen-3.6-27B-JANG_3L
Text Generation • 35B • Updated • 19
bearzi/Qwen-3.6-27B-JANG_3K
Text Generation • 41B • Updated • 13
bearzi/Qwen-3.6-27B-JANG_2S
Text Generation • 39B • Updated • 11
bearzi/Qwen-3.6-27B-JANG_2M
Text Generation • 42B • Updated • 15
bearzi/Qwen-3.6-27B-JANG_2L
Text Generation • 48B • Updated • 13
bearzi/Qwen-3.6-27B-JANG_1L
Text Generation • 53B • Updated • 16
bearzi/gemma-4-31B-it-JANG_1L
Text Generation • 61B • Updated • 157 • 11
bearzi/Qwen3.6-35B-A3B-JANG_3L
Text Generation • 38B • Updated • 39 • 1
bearzi/Qwen3.6-35B-A3B-oQ6
Text Generation • 35B • Updated • 45 • 4
bearzi/Qwen3.6-35B-A3B-oQ4
Text Generation • 35B • Updated • 57 • 5
bearzi/Qwen3.6-35B-A3B-oQ3
Text Generation • 35B • Updated • 154 • 4
bearzi/Qwen3.6-35B-A3B-oQ2
Text Generation • 35B • Updated • 176 • 7
bearzi/Qwen3.6-35B-A3B-oQ8
Text Generation • 35B • Updated • 38 • 5
bearzi/Trinity-Nano-Preview-oQ8
Text Generation • 6B • Updated • 18 • 1
bearzi/Qwen3-Coder-Next-oQ8
Text Generation • 80B • Updated • 46 • 1
bearzi/Qwen3-Coder-Next-oQ6
Text Generation • 80B • Updated • 40
bearzi/Qwen3-Coder-Next-oQ4
Text Generation • 80B • Updated • 170 • 2
bearzi/Qwen3-Coder-Next-oQ3
Text Generation • 80B • Updated • 173 • 2
bearzi/Qwen3-Coder-Next-oQ2
Text Generation • 80B • Updated • 245 • 3