majentik/gemma-4-E2B-it-RotorQuant-MLX-2bit
Image-Text-to-Text • 5B • Updated • 37
Volodymyr IERMOLAIEV PRO
majentik
AI & ML interests
Bleeding-edge AI models and most prominent ML open-source projects.
Recent Activity
updated a model 20 days ago
majentik/garden updated a model 20 days ago
majentik/MobileGaze-MobileOne-S0-MLX-fp32 published a model 20 days ago
majentik/MobileGaze-MobileOne-S0-MLX-fp32Organizations
majentik/Qwen3.6-35B-A3B-RotorQuant-MLX-6bit
Text Generation • 35B • Updated • 117
majentik/gemma-4-31B-TurboQuant-MLX-4bit
Image-Text-to-Text • 31B • Updated • 88 • 2
majentik/Leanstral-TurboQuant-MLX-2bit
Text Generation • 238B • Updated • 39
majentik/gemma-4-E4B-RotorQuant-MLX-4bit
Image-Text-to-Text • 8B • Updated • 50 • 1
majentik/Qwen3.5-27B-RotorQuant-MLX-8bit
Text Generation • 27B • Updated • 48
majentik/gemma-4-26B-A4B-RotorQuant-MLX-8bit
Image-Text-to-Text • 26B • Updated • 40
majentik/gemma-4-26B-A4B-it-RotorQuant-MLX-2bit
Image-Text-to-Text • 26B • Updated • 182
majentik/Qwen3.6-35B-A3B-RotorQuant-MLX-8bit
Text Generation • 35B • Updated • 122
majentik/gpt-oss-20b-TurboQuant-MLX-4bit
Text Generation • 21B • Updated • 345 • 2
majentik/MiniMax-M2.7-TurboQuant-MLX-3bit
Text Generation • 229B • Updated • 80
majentik/Qwen3.6-35B-A3B-TurboQuant-MLX-4bit
Text Generation • 35B • Updated • 367 • 16
majentik/Nemotron-3-Nano-30B-A3B-RotorQuant-MLX-4bit
Text Generation • 5B • Updated • 21
majentik/gemma-4-26B-A4B-RotorQuant-MLX-2bit
Image-Text-to-Text • 26B • Updated • 126
majentik/gemma-4-31B-it-TurboQuant-MLX-8bit
Image-Text-to-Text • 31B • Updated • 153 • 3
majentik/gemma-4-E2B-RotorQuant-MLX-8bit
Image-Text-to-Text • 5B • Updated • 14
majentik/Nemotron-3-Nano-4B-TurboQuant-MLX-8bit
Text Generation • 4B • Updated • 73
majentik/gemma-4-31B-it-RotorQuant-MLX-4bit
Image-Text-to-Text • 31B • Updated • 42 • 2
majentik/Qwen3.6-35B-A3B-MLX-MXFP4
Text Generation • 35B • Updated • 78
majentik/gemma-4-26B-A4B-it-RotorQuant-MLX-4bit
Image-Text-to-Text • 26B • Updated • 51
majentik/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-mmproj-F16
Image-Text-to-Text • Updated
majentik/gemma-4-31B-TurboQuant-MLX-8bit
Image-Text-to-Text • 31B • Updated • 34 • 1
majentik/gpt-oss-20b-TurboQuant-MLX-2bit
Text Generation • 21B • Updated • 209
majentik/gemma-4-E4B-RotorQuant-MLX-8bit
Image-Text-to-Text • 8B • Updated • 35 • 1
majentik/MiniMax-M2.7-TurboQuant-MLX-5bit
Text Generation • 229B • Updated • 41 • 1
majentik/gemma-4-26B-A4B-RotorQuant-MLX-4bit
Image-Text-to-Text • 26B • Updated • 34
majentik/Qwen3.5-27B-RotorQuant-MLX-4bit
Text Generation • 27B • Updated • 46 • 1
majentik/Qwen3.6-35B-A3B-TurboQuant-MLX-3bit
Text Generation • 35B • Updated • 298 • 6
majentik/MiniMax-M2.7-TurboQuant-MLX-4bit
Text Generation • 229B • Updated • 46
majentik/Nemotron-3-Nano-4B-RotorQuant-MLX-2bit
Text Generation • 4B • Updated • 24