majentik/LFM2.5-8B-A1B-MLX-MXFP4
Text Generation • 2B • Updated • 236
Volodymyr IERMOLAIEV PRO
majentik
AI & ML interests
Bleeding-edge AI models and most prominent ML open-source projects.
Recent Activity
updated a dataset 5 days ago
majentik/SASRBench-v1 published a dataset 5 days ago
majentik/SASRBench-v1 updated a dataset 5 days ago
majentik/WildASROrganizations
majentik/LFM2.5-8B-A1B-MLX-8bit
Text Generation • 2B • Updated • 41
majentik/LFM2.5-8B-A1B-MLX-6bit
Text Generation • 2B • Updated • 228
majentik/LFM2.5-8B-A1B-MLX-5bit
Text Generation • 2B • Updated • 228
majentik/LFM2.5-8B-A1B-MLX-4bit
Text Generation • 2B • Updated • 36
majentik/LFM2.5-8B-A1B-MLX-3bit
Text Generation • 1B • Updated • 194
majentik/Ornith-1.5-35B-A3B-MLX-MXFP4
Image-Text-to-Text • 7B • Updated • 237
majentik/Ornith-1.5-35B-A3B-MLX-5bit
Image-Text-to-Text • 7B • Updated • 172
majentik/Ornith-1.5-35B-A3B-MLX-3bit
Image-Text-to-Text • 6B • Updated • 211
majentik/Ornith-1.5-35B-A3B-MLX-2bit
Image-Text-to-Text • 5B • Updated • 230
majentik/Gemma-4-E4B-BF16-MERaLiON-Speech-LoRA-SG-MLX
Automatic Speech Recognition • Updated • 58
majentik/Gemma-4-E4B-MERaLiON-Speech-LoRA-MNSC-MLX
Automatic Speech Recognition • Updated • 45
majentik/MERaLiON-3-10B-MLX
Automatic Speech Recognition • Updated • 99
majentik/MERaLiON-3-3B-ASR-MLX-8bit
Automatic Speech Recognition • 1B • Updated • 30
majentik/gpt-oss-120b-TurboQuant-MLX-4bit
Text Generation • 22B • Updated • 747 • 1
majentik/UI-Mate-27B-MLX-MXFP4
Image-Text-to-Text • 6B • Updated • 17
majentik/UI-Mate-27B-MLX-8bit
Image-Text-to-Text • 8B • Updated • 20
majentik/UI-Mate-27B-MLX-6bit
Image-Text-to-Text • 6B • Updated • 20
majentik/UI-Mate-27B-MLX-5bit
Image-Text-to-Text • 6B • Updated • 22
majentik/UI-Mate-27B-MLX-4bit
Image-Text-to-Text • 6B • Updated • 30
majentik/UI-Mate-27B-MLX-3bit
Image-Text-to-Text • 5B • Updated • 37
majentik/UI-Mate-27B-MLX-2bit
Image-Text-to-Text • 4B • Updated • 30
majentik/Nemotron-3-Nano-30B-A3B-TurboQuant-MLX-2bit
Text Generation • 3B • Updated • 523
majentik/Qwen3.6-35B-A3B-RotorQuant-MLX-2bit
Text Generation • 4B • Updated • 1.46k • 10
majentik/Qwen3.5-27B-RotorQuant-GGUF-Q2_K
Text Generation • 27B • Updated • 133 • 2
majentik/gemma-4-26B-A4B-it-RotorQuant-MLX-8bit
Image-Text-to-Text • 8B • Updated • 166 • 1
majentik/Qwen3.5-27B-RotorQuant-GGUF-IQ4_XS
Text Generation • 27B • Updated • 103
majentik/Qwen3.6-35B-A3B-RotorQuant-GGUF-Q8_0
Image-Text-to-Text • 35B • Updated • 210
majentik/gemma-4-E2B-it-RotorQuant-MLX-2bit
Image-Text-to-Text • 0.9B • Updated • 84
majentik/Qwen3.6-35B-A3B-RotorQuant-MLX-6bit
Text Generation • 8B • Updated • 352