vanch007/Ming-3.0-tts-tiny-mlx-8bit
Pure Apple Silicon MLX native port of inclusionAI/Ming-3.0-tts-tiny (7.9B MoE with 128 Experts + 1 Shared Expert + KDA Attention) in 8-bit Quantized (Recommended Mainline).
- Architecture: 128 Routed Experts + 1 Shared Expert + KDA Recurrent Linear Attention
- Size: 9.78 GB
- Zero Triton: Pure Metal acceleration on Apple Silicon (M1/M2/M3/M4)
Sample Audios
| Task | Text | Audio |
|---|---|---|
| Podcast | speaker_1: ไฝ ๆ่ฟๆฏไธๆฏๅๅป้ฃๅฎถ้ข้ฆไบ๏ผ speaker_2: ๅฏนๅ๏ผๆไบๅไธชๅฐๆถ็้๏ผไธ่ฟ็็ๅผๅพใ | Audio |
| Lingxiaomeng | ๅคๆ็ๅพฎ้ฃๅนๆฃไบ็ฝๅคฉ็ๅงๅฃ๏ผๆฟๅฅฝๆขฆๅธธไผดไฝ ๅทฆๅณใ | Audio |
| Text Norm | ่ฎขๅๅท 20250317๏ผๅ ฑ 3 ไปถๅๅ๏ผๅ่ฎก ยฅ1,280.50๏ผ้ข่ฎก 3-5 ๅคฉ้่พพใ | Audio |
| Fast Speed | ไปๆ็่งๆตๅฐๅจไบๅฑๆฃๅผๅๅผๅงใ | Audio |
| Sad Emotion | ๆๆ็ๆต่ฏ้ฝ้่ฟไบใ | Audio |
- Downloads last month
- 72
Hardware compatibility
Log In to add your hardware
Quantized
Model tree for vanch007/Ming-3.0-tts-tiny-mlx-8bit
Base model
inclusionAI/Ming-3.0-tts-tiny