Tencent open-sources Hy-Memory-30B-A3B under Apache-2.0

tencent · hf · 2026-10-15

Tencent released Hy-Memory-30B-A3B on Hugging Face: a conversational text-generation model with a hyv3 architecture, roughly 30B total parameters with 3B active (A3B), bilingual English/Chinese, open-sourced under Apache-2.0 with an accompanying paper (arXiv:2610.22196). The "Memory" naming suggests a memory-oriented design; details are in the paper.

Related event: Tencent Hunyuan Open-Sources Hy Memory 2.0 Stack, Claims It Beats Claude Opus 5 at Memory(7 posts)→

Original post →

More from Models

• Reflection's 501B MoE Beam hits 463 tok/s on 8x GB200 with NVFP4 at day 0 — zhyncs42 · 2026-10-16
• LMArena launches Agent Arena and Code Arena leaderboards for model comparison — arena · 2026-10-16
• Third-party tests find NVIDIA Nemotron-3.5 Bolt underperforms nano on pandas/numpy and decision-making tasks — norenEnmotalen · 2026-10-16
• Reflection open-sources Beam under Apache 2.0 with 40+ partner ecosystem — bhutanisanyam1 · 2026-10-16
• One Prompt, 629 Lines: IQuest-Q1 Builds a Deep-Sea Submarine Game in 2 Minutes — Div_pradeep · 2026-10-16
• Swapping RLM sub-calls for Jev: half the cost, 6x faster at 1M tokens — lateinteraction · 2026-10-16

Models channel →