Text-to-speech models quantized for mlx-audio; every tier passed a multilingual synthesis smoke gate (ASR round-trip CER) before upload.
Volodymyr IERMOLAIEV PRO
majentik
AI & ML interests
Bleeding-edge AI models and most prominent ML open-source projects.
Recent Activity
updated a collection about 11 hours ago
TTS on Apple Silicon (MLX) updated a collection about 11 hours ago
TTS on Apple Silicon (MLX) updated a model about 11 hours ago
majentik/Audio8-TTS-Preview-0.6b-MLX-4bitOrganizations
models 398
majentik/garden
Text Generation • Updated
majentik/Audio8-TTS-Preview-0.6b-MLX-4bit
Text-to-Speech • 0.9B • Updated
majentik/Audio8-TTS-Preview-0.6b-MLX-8bit
Text-to-Speech • 0.9B • Updated
majentik/DeepSeek-V4-Flash-0731-GGUF-Q2_K
Text Generation • 284B • Updated • 125
majentik/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-TurboQuant-GGUF-MXFP4_MOE
Image-Text-to-Text • 32B • Updated • 122
majentik/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-TurboQuant-GGUF-Q8_0
Image-Text-to-Text • 32B • Updated • 26 • 1
majentik/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-TurboQuant-GGUF-Q5_K_M
Image-Text-to-Text • 32B • Updated • 44
majentik/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-TurboQuant-GGUF-Q4_K_M
Image-Text-to-Text • 32B • Updated • 52
majentik/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-TurboQuant-GGUF-IQ4_XS
Image-Text-to-Text • 32B • Updated • 65 • 1
majentik/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-TurboQuant-GGUF-Q3_K_M
Image-Text-to-Text • 32B • Updated • 26
datasets 14
majentik/SASRBench-v1
Viewer • Updated • 3.75k • 59
majentik/WildASR
Viewer • Updated • 10.1k • 81
majentik/garden-quant-bench
Viewer • Updated • 71 • 88
majentik/ultradata-sft-calib
Viewer • Updated • 2.1k • 59
majentik/ultradata-math-calib
Viewer • Updated • 4.1k • 46
majentik/ultra-fineweb-calib
Viewer • Updated • 5.12k • 11
majentik/fleurs-ar-asr
Viewer • Updated • 428 • 24 • 1
majentik/ifeval
Viewer • Updated • 541 • 18 • 1
majentik/wikitext-2-ppl
Viewer • Updated • 4.36k • 38 • 1
majentik/gsm8k
Viewer • Updated • 1.32k • 17