Tencent open-sources Hunyuan Hy4: 770B MoE with 1M context
TencentHunyuan · x · 2026-08-30
Tencent has open-sourced Hunyuan Hy4 preview under Apache 2.0. The flagship MoE model features 770B total parameters (49B active), 1M context window, and a native MTP layer for speculative decoding. In blind evaluations by 163 internal experts across 203 real engineering tasks, Hy4 scored 2.99, edging out GLM 5.3 (2.92) and Kimi K3 (2.94). It was trained on real production workflows including software engineering, data analysis, and research.
Related event: Tencent Open-Sources 770B MoE Hunyuan Hy4 Preview(2 posts)→
More from Models
- 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 Hunyuan Hy4-preview runs in vLLM day 0: 770B MoE with 1M context — TencentHunyuan · 2026-08-30
- User complains about Anthropic's overly strict safety blocking on benign projects — BLUECOW009 · 2026-08-30