Skip to content

tokimoa

Stockmark-DocReasoner-Qwen2.5-VL-32B-MLX-4bit

tokimoa/Stockmark-DocReasoner-Qwen2.5-VL-32B-MLX-4bit

Stockmark-DocReasoner-Qwen2.5-VL-32B-MLX-4bit is a image-text-to-text model from tokimoa. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for mlx. The card lists the license as apache-2.0.

Stockmarkの Stockmark-DocReasoner-Qwen2.5-VL-32B(日本語ドキュメント理解・推論特化VLM。製造業ドメイン強化・GENIAC支援・CoT推論対応)を、公式BF16重みからMLX 4bit(group size 64、実効4.74bpw)に量子化したものです。日本語ビジネス文書での検証済みで公開しています。

Downloads · 30 days

141

25% of all-time downloads

All-time downloads

562

Public

Parameters

33.5B

19.8 GB on disk

Likes

0

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors19.8 GB · 100%

Parameter types

How the weights are stored.

U3232.8B · 98%

Base models

Task
Image-Text-to-Text
Library
mlx
Type
qwen2_5_vl
License
apache-2.0
Languages
ja
Created
Jul 26, 2026
Updated
Jul 28, 2026