Qwen3 TTS 12Hz 0.6B Base — MLX 8-bit

MLX 8-bit quantized conversion of Qwen/Qwen3-TTS-12Hz-0.6B-Base for Apple Silicon inference.

Usage

Used by speech-swift Qwen3TTS module:

let model = try await Qwen3TTSModel.fromPretrained(
    modelId: "aufklarer/Qwen3-TTS-12Hz-0.6B-Base-MLX-8bit"
)
let audio = try model.synthesize("Hello, world!")

audio speak "Hello, world!" --model base-8bit -o output.wav

Model Details

Architecture: Qwen3-TTS (Talker transformer + Code Predictor + Mimi speech tokenizer decoder)
Parameters: 0.6B
Quantization: 8-bit (MLX, talker + code predictor)
Size: ~1.3 GB
Sample rate: 24 kHz
Codec rate: 12.5 Hz

Variants

Variant	Quantization	Size	Model ID
0.6B 4-bit	4-bit	~981 MB	aufklarer/Qwen3-TTS-12Hz-0.6B-Base-MLX-4bit
0.6B 8-bit	8-bit	~1.3 GB	aufklarer/Qwen3-TTS-12Hz-0.6B-Base-MLX-8bit
1.7B 4-bit	4-bit	~1.7 GB	aufklarer/Qwen3-TTS-12Hz-1.7B-Base-MLX-4bit
1.7B 8-bit	8-bit	~2.8 GB	aufklarer/Qwen3-TTS-12Hz-1.7B-Base-MLX-8bit

Downloads last month: 94

Safetensors

Model size

0.5B params

Tensor type

BF16

U32

MLX

Hardware compatibility

8-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for aufklarer/Qwen3-TTS-12Hz-0.6B-Base-MLX-8bit

Base model

Qwen/Qwen3-TTS-12Hz-0.6B-Base

Quantized

(12)

this model

Collection including aufklarer/Qwen3-TTS-12Hz-0.6B-Base-MLX-8bit

MLX Speech Models

Collection

Speech AI models for Apple Silicon via MLX. ASR, TTS, VAD, diarization, speaker embedding. • 29 items • Updated 2 days ago • 1