PowerBeef02/Qwen3-TTS-12Hz-1.7B-CustomVoice-4bit

Same weights, repacked vs mlx-community/Qwen3-TTS-12Hz-1.7B-CustomVoice-4bit. Same weights in different files (re-saved, re-sharded or new metadata), plus 2 new tensors.

Tensors changed: lm_head 0/45, Embeddings 0/16, Norms 0/134, MLP 0/305, Attention 0/396, other 0/7

On the Hub · Downloads on Model Pulse