# Tencent releases Hunyuan Hy4-flash multimodal MoE

> The lightweight, mixture-of-experts model adds vision and text instruction-following to Tencent's open Hunyuan lineup.

Published by The Open Weights on Nov 17, 2026. Canonical: https://theopenweights.com/news/hunyuan-hy4-flash-wii7

## Key facts

- Company: Tencent
- Model: Hunyuan Hy4-flash
- Version: 4-flash
- Category: Vision-Language
- Modalities: Text / LLM, Vision-Language
- License: Other (Open weights, commercial use allowed)
- Context window: 1.0M tokens
- Architecture: HYV4FlashForConditionalGeneration
- Precision: BF16
- Weights size: 440.5 GB
- Significance: notable
- Published: 2026-11-17
- Last verified: 2026-11-20
- Hugging Face: https://huggingface.co/tencent/Hy4-flash
- Canonical URL: https://theopenweights.com/news/hunyuan-hy4-flash-wii7

Tencent has quietly released **Hunyuan Hy4-flash**, a new multimodal model in its Hunyuan family, now available on [Hugging Face](https://huggingface.co/tencent/Hy4-flash). The "flash" branding signals a model tuned for speed and efficiency, aimed at latency-sensitive workloads rather than maximum capability.

The release is built around a mixture-of-experts (MoE) architecture, which activates only a portion of the model's parameters for any given input. That approach lets developers tap a large total parameter pool while keeping inference costs closer to those of a smaller dense model — a practical fit for the "flash" positioning.

## What it does

Hy4-flash is a vision-language model with text capabilities, meaning it can take in both images and text and respond to instructions. Key points from the record:

- Primary modality is vision-language, with text handling alongside
- MoE design for efficient inference
- Released as an instruction-tuned model under a custom (non-standard) license

Specifics such as parameter counts and context length were not detailed in the release metadata, so teams evaluating the model will want to check the model card directly for configuration and usage terms.

**Why it matters:** Tencent is one of several large Chinese labs steadily shipping open-weight models, and a fast multimodal MoE broadens the options for developers who need image understanding without the overhead of a frontier-scale system. As always, the custom license means the details of commercial use deserve a close read before deployment.

## Get the model

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

## Sources

- [tencent/Hy4-flash](https://huggingface.co/tencent/Hy4-flash) — Hugging Face, Nov 17, 2026

---
Source: The Open Weights (https://theopenweights.com/). Aggregated and written by Claude, curated by humans. Cite as: "Tencent releases Hunyuan Hy4-flash multimodal MoE", The Open Weights, Nov 17, 2026, https://theopenweights.com/news/hunyuan-hy4-flash-wii7