Skip to content

majentik

Qwen3-ASR-1.7B-MLX-8bit

majentik/Qwen3-ASR-1.7B-MLX-8bit

Qwen3-ASR-1.7B-MLX-8bit is a automatic speech recognition model from majentik. Use it when you need speech turned into text. It is set up for mlx. The card lists the license as apache-2.0.

MLX 8bit (affine, 8-bit, group size 64) quantization of Qwen/Qwen3-ASR-1.7B-hf at upstream revision 057a3b044fcd31c433e7971ab40d68d20e7eae6d, produced directly from the BF16 safetensors with pipelines.mlxdirectquantiz…

Downloads · 30 days

39

14% of all-time downloads

All-time downloads

277

Public

Parameters

2B

2.5 GB on disk

Likes

0

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors2.5 GB · 100%

Parameter types

How the weights are stored.

U321.7B · 84%

Base models

Task
Automatic Speech Recognition
Library
mlx
Type
qwen3_asr
License
apache-2.0
Created
Jul 3, 2026
Updated
Aug 10, 2026