aufklarer/Qwen3-ASR-0.6B-MLX-4bitQwen3 ASR 0.6B — MLX 4 bit MLX 4 bit quantized conversion of Qwen/Qwen3 ASR 0.6B for Apple Silicon inference. Usage Used by speech swift Qwen3ASR module: Model Details Architecture : Qwen3 ASR encoder decoder (Whisper style audio encoder + Qwen3 text decoder) Parameters : 0.6B Quantization : 4 bit (MLX) Size : ~680 MB Languages : Multilingual (EN, ZH, JA, KO, FR, DE, ES, and more) Guide : soniqo.audio/guides/transcribe Docs : soniqo.audio GitHub : soniqo/speech swift

Qwen3-ASR-0.6B-MLX-4bit

PUBLIC

Mirrored

MLX 4-bit quantized conversion of Qwen/Qwen3-ASR-0.6B for Apple Silicon inference.

Libraries:mlxLicense:apache-2.0

imported

huggingface

minio

mlx

safetensors

qwen3_asr

speech

asr

qwen3

base_model:Qwen/Qwen3-ASR-0.6B

base_model:quantized:Qwen/Qwen3-ASR-0.6B

license:apache-2.0

4-bit

0downloads0likesmlxLicense:apache-2.0

Model Card

Edit

Qwen3 ASR 0.6B — MLX 4-bit

MLX 4-bit quantized conversion of Qwen/Qwen3-ASR-0.6B for Apple Silicon inference.

Usage

Used by speech-swift Qwen3ASR module:

let model = try await Qwen3ASRModel.fromPretrained()
let text = model.transcribe(audio: samples, sampleRate: 16000)

audio transcribe audio.wav

Model Details

Architecture: Qwen3-ASR encoder-decoder (Whisper-style audio encoder + Qwen3 text decoder)
Parameters: 0.6B
Quantization: 4-bit (MLX)
Size: ~680 MB
Languages: Multilingual (EN, ZH, JA, KO, FR, DE, ES, and more)

Guide: soniqo.audio/guides/transcribe
Docs: soniqo.audio
GitHub: soniqo/speech-swift

Inference Providers

This model isn't deployed by any Inference Provider yet. Deploy this model →

Model details

Model size

0.6B params

Architecture

Qwen3

Source

Mirrored from an external registry.

Last synced 7/28/2026

Model tree for aufklarer/Qwen3-ASR-0.6B-MLX-4bit

Base model

Qwen/Qwen3-ASR-0.6B

Commit History

No commits available

We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy