Downloads · 30 days
24
23% of all-time downloads
Qwen3-ASR-1.7B-MLX-4bit
doggy8088/Qwen3-ASR-1.7B-MLX-4bit
Qwen3-ASR-1.7B-MLX-4bit is a automatic speech recognition model from doggy8088. Use it when you need speech turned into text. It is set up for mlx.
This repo contains an MLX conversion of Qwen/Qwen3-ASR-1.7B.
All-time downloads
106
Public
Parameters
2.3B
1.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.3 GB · 100%
Parameter types
How the weights are stored.
U322.3B · 100%
Base models
Model card
From the Hugging Face model README
doggy8088/Qwen3-ASR-1.7B-MLX-4bit
This repo contains an MLX conversion of Qwen/Qwen3-ASR-1.7B.
Variant
- Format: MLX safetensors
- Weights dtype: bfloat16
- Quantization: 4-bit
- Custom architecture helper:
qwen3_asr_mlx.py
Files
model*.safetensors: converted MLX weightsconfig.json: converted model configpreprocessor_config.json,tokenizer_config.json,vocab.json,merges.txt: tokenizer / processor assets copied from the source modelqwen3_asr_mlx.py: custom MLX architecture + processor helper used for this conversion
Notes
- Source model:
Qwen/Qwen3-ASR-1.7B - Local conversion directory:
Qwen3-ASR-1.7B-MLX-4bit - This is an Apple Silicon / MLX-oriented conversion.
- For quantized variants, quantizable linear layers are quantized while non-quantizable layers remain in floating point.
- Task
- Automatic Speech Recognition
- Library
- mlx
- Type
- qwen3_asr
- Created
- May 8, 2026
- Updated
- May 8, 2026