majentik/Voxtral-4B-TTS-2603-RotorQuant-MLX-4bit
Text-to-Speech • Updated • 18 • 1
Volodymyr IERMOLAIEV PRO
majentik
AI & ML interests
Bleeding-edge AI models and most prominent ML open-source projects.
Recent Activity
updated a model about 2 hours ago
majentik/cohere-transcribe-arabic-07-2026-MLX-4bit updated a model about 2 hours ago
majentik/cohere-transcribe-arabic-07-2026-MLX-6bit updated a model about 2 hours ago
majentik/cohere-transcribe-arabic-07-2026-MLX-8bitOrganizations
majentik/Voxtral-4B-TTS-2603-RotorQuant-MLX-2bit
Text-to-Speech • Updated • 4
majentik/Qwen3.6-35B-A3B-TurboQuant-MLX-8bit
Text Generation • 10B • Updated • 838 • 7
majentik/Qwen3.6-35B-A3B-TurboQuant-MLX-6bit
Text Generation • 8B • Updated • 718 • 1
majentik/Qwen3.6-35B-A3B-TurboQuant-MLX-5bit
Text Generation • 7B • Updated • 579
majentik/Qwen3.6-35B-A3B-TurboQuant-MLX-4bit
Text Generation • 6B • Updated • 2.18k • 14
majentik/Qwen3.6-35B-A3B-TurboQuant-MLX-3bit
Text Generation • 5B • Updated • 1.27k • 6
majentik/Qwen3.6-35B-A3B-TurboQuant-MLX-2bit
Text Generation • 4B • Updated • 970 • 3
majentik/Qwen3.6-35B-A3B-RotorQuant-MLX-8bit
Text Generation • 10B • Updated • 340
majentik/Qwen3.6-35B-A3B-RotorQuant-MLX-6bit
Text Generation • 8B • Updated • 508
majentik/Qwen3.6-35B-A3B-RotorQuant-MLX-5bit
Text Generation • 7B • Updated • 573
majentik/Qwen3.6-35B-A3B-RotorQuant-MLX-4bit
Text Generation • 6B • Updated • 956 • 5
majentik/Qwen3.6-35B-A3B-RotorQuant-MLX-3bit
Text Generation • 5B • Updated • 751 • 3
majentik/Qwen3.6-35B-A3B-RotorQuant-MLX-2bit
Text Generation • 4B • Updated • 2.34k • 8
majentik/Qwen3.5-397B-A17B-TurboQuant-MLX-8bit
Image-Text-to-Text • 112B • Updated • 71 • 1
majentik/Qwen3.5-397B-A17B-TurboQuant-MLX-4bit
Image-Text-to-Text • 62B • Updated • 65
majentik/Qwen3.5-397B-A17B-RotorQuant-MLX-8bit
Image-Text-to-Text • 112B • Updated • 48
majentik/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-mmproj-F16
Image-Text-to-Text • Updated
majentik/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-TurboQuant-MLX-8bit-TQ-KV
Text Generation • Updated
majentik/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-TurboQuant-MLX-8bit
Text Generation • 10B • Updated • 34
majentik/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-TurboQuant-MLX-6bit-TQ-KV
Text Generation • Updated
majentik/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-TurboQuant-MLX-6bit
Text Generation • 8B • Updated • 34
majentik/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-TurboQuant-MLX-5bit-TQ-KV
Text Generation • Updated
majentik/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-TurboQuant-MLX-5bit
Text Generation • 7B • Updated • 30
majentik/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-TurboQuant-MLX-4bit-TQ-KV
Text Generation • Updated
majentik/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-TurboQuant-MLX-4bit
Text Generation • 6B • Updated • 39
majentik/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-TurboQuant-MLX-3bit-TQ-KV
Text Generation • Updated
majentik/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-TurboQuant-MLX-3bit
Text Generation • 5B • Updated • 33
majentik/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-TurboQuant-MLX-2bit-TQ-KV
Text Generation • Updated
majentik/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-TurboQuant-MLX-2bit
Text Generation • 4B • Updated • 52