HU
HunyuanImage-3.0-Instruct
Vision modelTencent HunyuanImage-3.0-Instruct
Release date: 2026-01-28Views: 777
Parameters
80B
Context length
128K
Multilingual
Supported
Reasoning ability
5/5
Tencent HunyuanImage-3.0-Instruct is an AI model published by Tencent AI Lab, released on 2026-01-28, for Vision model, with 80B parameters, and 128K context length, requiring about 170GB storage.
Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology
HunyuanImage-3.0-Instruct
Model basics
Reasoning traces
No data
Thinking modes
Standard Mode (Default)Thinking Mode
Context length
128K tokens
Max output length
4K tokens
Model type
Vision model
Modality (in / out)
Text, Image → Image
Release date
2026-01-28
Model file size
170GB
MoE architecture
Yes
Total params / Active params
80B / 13B
Knowledge cutoff
No data
HunyuanImage-3.0-Instruct
Open source & experience
Code license
Weights license
Tencent Hunyuan Community License Agreement- Commercial use permitted
GitHub repo
Hugging Face
Live demo
HunyuanImage-3.0-Instruct
Official resources
Paper
DataLearnerAI blog
N/A
HunyuanImage-3.0-Instruct
API details
API speed
3/5
No public API pricing yet.
HunyuanImage-3.0-Instruct
Publisher
Tencent AI Lab
View publisher details Tencent HunyuanImage-3.0-Instruct
Model Overview
Tencent HunyuanImage-3.0-Instruct is an AI model published by Tencent AI Lab, released on 2026-01-28, for Vision model, with 80B parameters, and 128K context length, requiring about 170GB storage.
DataLearner on WeChat
Follow DataLearner on WeChat for AI model updates and research notes.
