Tencent Releases Hy4 Preview: 770B Parameter MoE Model for Coding and Research
pstAsiatech · x · 2026-08-30
Tencent has released a new open-source AI model named Hy4 preview, designed for coding and research tasks. The model uses a Mixture-of-Experts (MoE) architecture with a total of 770 billion parameters, though only about 49 billion are activated for any given text request.
Related event: Tencent Open-Sources 770B MoE Hunyuan Hy4 Preview(2 posts)→
More from Models
- NVIDIA reportedly buys Hugging Face for $12.9B; GLM-5.3-Flash and Qwen4 preview land same week — altryne · 2026-08-30
- Qwen3.8-Flash-Next-REAP-288 Released in BF16 and GGUF Formats — EyalToledano · 2026-08-30
- GLM 5.3 Flash Inference Extremely Slow on Apple Silicon — CentrifugalMalaise · 2026-08-30
- Study finds model rankings shift significantly on altered benchmark questions — abeirami · 2026-08-30
- OpenAI's unreleased Astra model leaks: first outputs of mozaik-alpha-fdm surface — gaganghotra_ · 2026-08-30
- Tencent open-sources Hunyuan Hy4: 770B MoE with 1M context — TencentHunyuan · 2026-08-30