---
title: Qwen3-ASR-1.7B-4bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/Qwen3-ASR-1.7B-4bit"
md_url: "https://www.modelscope.cn/models/mlx-community/Qwen3-ASR-1.7B-4bit.md"
repository: mlx-community/Qwen3-ASR-1.7B-4bit
last_updated: 2026-02-02
license: apache-2.0
model_type:
  - qwen3_asr
architectures:
  - Qwen3ASRForConditionalGeneration
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 1368
stars: 0
tags:
  - mlx
  - speech-to-text
  - speech
  - transcription
  - asr
  - stt
  - mlx-audio
---

# Qwen3-ASR-1.7B-4bit

> Qwen3-ASR-1.7B-4bit - mlx-community 在 ModelScope 开源的模型。mlx-community/Qwen3-ASR-1.7B-4bit

mlx-community/Qwen3-ASR-1.7B-4bit 是 ModelScope 魔搭社区上的机器学习模型，采用 apache-2.0 许可。

- **Repository**: mlx-community/Qwen3-ASR-1.7B-4bit
- **License**: apache-2.0
- **Tags**: mlx, speech-to-text, speech, transcription, asr, stt, mlx-audio
- **Downloads**: 1368
- **Stars**: 0
- **Last updated**: 2026-02-02

Source: https://www.modelscope.cn/models/mlx-community/Qwen3-ASR-1.7B-4bit

---

# mlx-community/Qwen3-ASR-1.7B-4bit

This model was converted to MLX format from [`Qwen/Qwen3-ASR-1.7B`](https://huggingface.co/Qwen/Qwen3-ASR-1.7B) using mlx-audio version **0.3.1**.

Refer to the [original model card](https://huggingface.co/Qwen/Qwen3-ASR-1.7B) for more details on the model.

## Use with mlx-audio

```bash
pip install -U mlx-audio
```

### CLI Example:
```bash
python -m mlx_audio.stt.generate --model mlx-community/Qwen3-ASR-1.7B-4bit --audio "audio.wav"
```

### Python Example:
```python        
from mlx_audio.stt.utils import load_model
from mlx_audio.stt.generate import generate_transcription

model = load_model("mlx-community/Qwen3-ASR-1.7B-4bit")
transcription = generate_transcription(
    model=model,
    audio_path="path_to_audio.wav",
    output_path="path_to_output.txt",
    format="txt",
    verbose=True,
)
print(transcription.text)

```