# Tencent releases Hunyuan Hy4, an MoE vision-language model

> The instruction-tuned, mixture-of-experts model handles both images and text under an open weights listing on Hugging Face.

Published by The Open Weights on Oct 29, 2026. Canonical: https://theopenweights.com/news/hunyuan-hy4-478a

## Key facts

- Company: Tencent
- Model: Hunyuan Hy4
- Version: Hy4
- Category: Text / LLM
- Modalities: Text / LLM, Vision-Language
- License: Other (Open weights, commercial use allowed)
- Context window: 1.0M tokens
- Architecture: HYV4VLForConditionalGeneration
- Precision: BF16
- Weights size: 1548.9 GB
- Significance: notable
- Published: 2026-10-29
- Last verified: 2026-11-20
- Hugging Face: https://huggingface.co/tencent/Hy4
- Canonical URL: https://theopenweights.com/news/hunyuan-hy4-478a

Tencent has published Hunyuan Hy4, a multimodal vision-language model, to [Hugging Face](https://huggingface.co/tencent/Hy4). The release extends the company's Hunyuan line into territory that pairs image understanding with text generation in a single system.

Hy4 is described as an instruction-tuned model built on a mixture-of-experts (MoE) architecture. MoE designs activate only a subset of their parameters for any given input, a technique that lets developers scale total capacity while keeping the compute cost of each inference in check. That approach has become a common thread across recent frontier-scale open releases.

## Why it matters

Vision-language models are the connective tissue for a growing set of applications — document parsing, UI automation, visual question answering, and multimodal assistants among them. A capable open-weights VLM from a company of Tencent's scale gives developers another foundation to build on without committing to a closed API.

A few practical notes from the listing:

- It is positioned as a vision-language model with text generation capability.
- It uses a mixture-of-experts architecture and is instruction-tuned.
- It ships under a custom license, so teams should review the terms before commercial use.

Tencent has not yet detailed parameter counts, context length, or benchmark results in the record available at launch. Prospective users will want to watch the [model card](https://huggingface.co/tencent/Hy4) for documentation, evaluation numbers, and licensing specifics as they are published.

## Get the model

- [Hugging Face](https://huggingface.co/tencent/Hy4)

## Sources

- [tencent/Hy4](https://huggingface.co/tencent/Hy4) — Hugging Face, Oct 29, 2026

---
Source: The Open Weights (https://theopenweights.com/). Aggregated and written by Claude, curated by humans. Cite as: "Tencent releases Hunyuan Hy4, an MoE vision-language model", The Open Weights, Oct 29, 2026, https://theopenweights.com/news/hunyuan-hy4-478a