Tencent releases Hy-Memory-30B-A3B, a 3B-active memory-focused model claiming to beat Opus
victormustar · x · 2026-10-16
Tencent published Hy-Memory-30B-A3B on Hugging Face, a 30B-total/3B-active model focused on memory, claiming "A 3B active model beats Opus 5 at memory." Its chat template ships dedicated tokens for thinking, tool calls/responses, and a conditional reasoning mode, signaling an agent/tool-use design. Independent benchmark evidence has not yet been released.
Related event: Tencent Hunyuan Open-Sources Hy Memory 2.0: 30B MoE Model for Agent Memory(5 posts)→
More from coding & agent
- Agent named 'Ilya' reportedly scores 1.1pt higher on benchmarks — daniel_mac8 · 2026-10-16
- Gemini CLI fix: substring matching inlined unrequested binary files into model context — priyanshu1976 · 2026-10-16
- Building AI agents on real healthcare claims data: the domain work that makes them work — alex_verem · 2026-10-16
- OpenAI stealth-testing mysterious internal model 'Aeon' in Codex desktop app and Dots — cedric_chee · 2026-10-16
- Vibe-coded iPhone Duo sniping bot built with Codex in 17 minutes, 41 tests passing — xiaohu · 2026-10-16
- Long-term multiplayer agent memory tool tops BEAM memory benchmark — CurieuxExplorer · 2026-10-16