Qwen3-TTS-12Hz-1.7B-CustomVoice-8bit
from Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice
Params
1.9B
Weights
≈ 2.4 GB
Mac memory
8 GB+
apache-2.0 · updated 2026-01-26
Apple silicon
Apple MLX models
5,841 models converted for Apple MLX, listed from Hugging Face’s mlx-community, refreshed 54m ago. Weights size and Mac memory are estimates from parameter count and quantisation.
Alert me about new Apple/MLX models
6 builds · clear filters
VibeVoice-Realtime-0.5B-fp16
from Qwen/Qwen2.5-0.5B
Params
1.0B
Weights
≈ 2.0 GB
Mac memory
8 GB+
mit · updated 2025-12-15
VibeVoice-Realtime-0.5B-8bit
from Qwen/Qwen2.5-0.5B
Params
1.0B
Weights
≈ 1.1 GB
Mac memory
8 GB+
mit · updated 2025-12-15
VibeVoice-Realtime-0.5B-4bit
from Qwen/Qwen2.5-0.5B
Params
1.0B
Weights
≈ 633 MB
Mac memory
8 GB+
mit · updated 2025-12-15
VibeVoice-Realtime-0.5B-6bit
from Qwen/Qwen2.5-0.5B
Params
1.0B
Weights
≈ 876 MB
Mac memory
8 GB+
mit · updated 2025-12-15
VibeVoice-Realtime-0.5B-5bit
from Qwen/Qwen2.5-0.5B
Params
1.0B
Weights
≈ 754 MB
Mac memory
8 GB+
mit · updated 2025-12-15