hy-memory-30b-a3b
hy-memory-30b-a3b is Text Generation model with 30B parameters, built with Transformers. Download, explore files and run it on Hugging Face.. It is ranked #776 on the Dev Radar, in AI dev tools, first seen 14 days ago and shared in 7 posts (245.4k views).
tencent/Hy-Memory-30B-A3B · Hugging Face Hugging Face Log In Sign Up ","eos_token":"<eos:6124c78e>","pad_token":"<｜hy_▁pad▁｜>"},"chat_template_jinja":"{# ----------‑‑‑ special token variables ‑‑‑---------- #}\n{%- set HYTK = '' %}\n{%- set bos_token = '<｜hy_begin▁of▁sentence｜>' %}\n{%- set pad_token = '<｜hy_▁pad▁｜>' %}\n{%- set user_token = '<｜hy_User｜>' %}\n{%- set assistant_token = '<｜hy_Assistant｜>' %}\n{%- set eos_token = '<eos:6124c78e>' %}\n{# ----------‑‑‑ tokens with md5 encoding (conditional on HYTK) ‑‑‑---------- #}\n{%- if HYTK %}\n {%- set think_begin_token = '<think:{}>'.format(HYTK) %}\n {%- set think_end_token =…
What people said about hy-memory-30b-a3b on X
🚀 Hy Memory 2.0 is out — open-source model, framework, and MemHub. Your private memory steward. Framework handles chat, work & code memories. #1 open-source on 4 benchmarks. Hy-Memory-30B-A3B beats Opus 5 across major frameworks. MemHub (CLI + Mac) syncs across 10+ AI tools. 💻➡️ 🔗 SDK & MemHub:…
— @TencentHunyuan, 14 days ago · 1.3k likes · see the post
A 3B active model beats Opus 5 at memory. We open-sourced the full stack — model, engine, and app. Hy Memory handles chat, work, and code memory in one layer, and it's first on all four benchmarks we ran, leading MemoryArena by 10.2 points while cutting memory volume 51.8% and recall tokens 39.3%. The model isn't…
— @TencentAI_News, 14 days ago · 1.1k likes · see the post
🚨重磅！3B激活参数模型直接干翻Opus 5，腾讯混元Hy Memory 2.0三层全部开源！ 模型、框架、应用一次全开放，让AI真正记得你说过什么、做到哪、代码为什么改。 关键亮点： 🔹性能反超：Hy-Memory-30B-A3B（约3B激活）在四套记忆系统平均分55.49，超越Opus 5的54.62，且可直接接入Mem0/MemOS/EverMemOS仍领先 🔹开源框架第一：覆盖聊天/工作/代码三大场景，在4个benchmark全面第一，MemoryArena领先10.2分 🔹更轻更准：记忆体积减少51.8%，召回token降低39.3%；内部助手多跳召回从50%直接拉到90%…
— @NFT_Chen, 14 days ago · 183 likes · see the post
Alternatives to hy-memory-30b-a3b
- goo.gle — Officially in beta, the AppFunctions API is opening up powerful new ways to integrate your functionality.
- Kimi AI with K3.1 Pro — Try Kimi K3.1 Pro to tackle complex coding projects, build 3D models, conduct financial research, and take on more…
- Agents in flight — Give it a try
- Baseten — This session is our most in-demand yet. See you there
- project-maya — Checkout Maya
- deepinfer — You gotta love Deepseek. This is awesome stuff!
hy-memory-30b-a3b in numbers
- Rank on the Dev Radar: #776 of 8798
- Shared in 7 posts by 5 accounts: @TencentHunyuan, @TencentAI_News, @NFT_Chen, @victormustar
- 245.4k views on those posts
- First seen 14 days ago, last shared 10 days ago
- Pricing seen by AGK Intelligence: not stated
- Market: AI dev tools
FAQ
What is hy-memory-30b-a3b?
Text Generation model with 30B parameters, built with Transformers. Download, explore files and run it on Hugging Face. It was first shared on X 14 days ago and is ranked #776 on the Dev Radar.
Is hy-memory-30b-a3b free?
Pricing is not stated on the page we read.
Who shared hy-memory-30b-a3b?
5 accounts on X, including @TencentHunyuan, @TencentAI_News, @NFT_Chen, in 7 posts totalling 245.4k views.
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 31.2k posts from 5k X accounts over the last 21 days, 8.8k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-10-30 20:27 UTC. Full method.