Skip to content

VoiceScribe

qwen3-5-0.8b-dictation-corrector-mlx-mixed46-g32

VoiceScribe/qwen3-5-0.8b-dictation-corrector-mlx-mixed46-g32

qwen3-5-0.8b-dictation-corrector-mlx-mixed46-g32 is a text generation model from VoiceScribe. Use it when you need the model to write or continue text. It is set up for mlx. The card lists the license as apache-2.0.

Default V15 R-3 corrector for Apple Silicon with ≥16 GB unified memory. PTQ on V15's bf16-fused weights via mlx-lm --quant-predicate mixed46 --q-group-size 32. Strictly Pareto-better than the V15 Q8 production mirror:…

Downloads · 30 days

30

6% of all-time downloads

All-time downloads

497

Public

Parameters

752M

502 MB on disk

Likes

1

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors482 MB · 96%

Parameter types

How the weights are stored.

U32752M · 100%

Base models

Task
Text Generation
Library
mlx
Type
qwen3_5
License
apache-2.0
Languages
ru
Created
May 27, 2026
Updated
May 27, 2026