Skip to content

hon9kon9ize

CantoneseLLM-v2.0-30B-A3B-Thinking

hon9kon9ize/CantoneseLLM-v2.0-30B-A3B-Thinking

CantoneseLLM-v2.0-30B-A3B-Thinking is a text generation model from hon9kon9ize. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.

This is the flagship release of CantoneseLLM v2. It is a 30.5B-parameter mixture-of-experts model (3.3B activated) based on Qwen3-30B-A3B that reasons and answers in Hong Kong Cantonese.

Downloads · 30 days

690

49% of all-time downloads

All-time downloads

1.4K

Public

Parameters

30.5B

61.1 GB on disk

Likes

3

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors61.1 GB · 100%

At a glance

Task
Text Generation
Library
transformers
License
apache-2.0
Model type
qwen3_moe
Access
Public
Created
Aug 1, 2026
Updated
Sep 9, 2026
SHA
9167e249

Base models

Task
Text Generation
Library
transformers
Type
qwen3_moe
License
apache-2.0
Languages
yue, zh, en
Created
Aug 1, 2026
Updated
Sep 9, 2026