Model reference · open weights
Hy4 is an open-weight language model from tencent, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
[](#license) [](https://huggingface.co/tencent/Hy4-preview) [](https://modelscope.cn/models/Tencent-Hunyuan/Hy4-preview) [](https://cnb.cool/ai-models/tencent/Hy4-preview) [](https://ai.gitcode.com/tencenthunyuan/Hy4-preview) 🖥️ <a href="https://aistudio.tencent.com/"<bOfficial Website</b</a | 💬 <a href="https://github.com/Tencent-Hunyuan/Hy4-preview"<bGitHub</b</a</p Table of Contents - Model Introduction - A New Flagship Generation - Built for Productivity - Benchmark Appendix - Known Limitations - News - Model Links - Quickstart - Deployment - vLLM - SGLang - Finetuning - Quantization - License - Contact Us Model Introduction Hy4 preview is a new-generation Mixture-of-Experts (MoE) flagship model developed by the Tencent Hy Team. The model comprises 770B total parameters, of which 49B are activated per token. The backbone consists of 78 layers, where the first layer uses a standard dense FFN and the remaining 77 layers replace it with MoE, each containing 256 routed experts and 1 shared expert; every token activates the top-8 routed experts along with the shared expert. In addition to the backbone, 1 native MTP layer (10B total parameters, 0.7B activated) is built in for speculative decoding. On the architecture side, inspired by DeepSeek and GLM, the attention module employs Gated DeepSeek Sparse Attention (Gated DSA) with IndexCache for cross-layer sparse index reuse. The residual pathway uses iHC (identity Hyper-Connections) to expand inter-layer information flow. Model Specifications The table below lists backbone parameters only, excluding the MTP layer. A New Flagship Generation We scaled Hy4 preview on three fronts: model size, context length, and training data. Stronger pre-training and a substantially larger post-training run compound into another step change in capability — the largest generation-over-generation gain we've measured, and enough to put Hy4 preview at the open-source frontier. Built for Productivity We partnered with top experts inside Tencent — such as software engineers, game developers, finance analysts, and security experts — and built training dat
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | tencent |
|---|---|
| Type | Language models |
| Parameters (lead) | 780.0B |
| Variants | 2 |
| Runs with | transformers |
| Released | 2026-08-27 |
| Popularity | 2k downloads / month |
| Likes | 316 |
| Licence | Open weights |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
Using it via the API
Once AxForge deploys hy4 for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (hy4 below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/chat/completions \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"hy4","messages":[{"role":"user","content":"Hello"}]}'
Licence
Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗