Hy-Memory-30B-A3B

Released
2026-10-16
Last refreshed
2026-10-21
Status
Researched today
Open sourceCommercial use: permittedAgents

Hy-Memory-30B-A3B is a released agents model with open-source; evaluate it while provider pricing coverage matures.

Tencent AI Lab releases · 10 in the last 12 months · this family litChangelog →
Specifications
Family
Hy-Memory
Released
2026-10-16
Parameters
30B
Architecture
Mixture of Experts
Specialization
agentic
Openness
Open source
License
Apache 2.0OSI-approvedPermitted
Weights
Available
Code
Unknown
Created by

AI innovations for societal improvement

Shenzhen, China
Founded 2016
Website
Pricing

No tracked provider pricing is available yet.

About

Hy-Memory-30B-A3B is Tencent Hunyuan's open-weight long-term-memory writer, a 30-billion-parameter mixture-of-experts model with about 3 billion active parameters, released October 16, 2026 with Hy-Memory 2.0. It runs the write path inside external memory frameworks (Mem0, MemOS and Hy-Memory), extracting what to remember from chat, work and code sessions and updating outdated memories, and Tencent reports it beats Claude Opus 5 and DeepSeek V4.1 Flash as a memory writer across those harnesses. Weights are on Hugging Face under Apache 2.0.

Providers

No active provider routes are tracked for this model yet.

Capabilities

No model capability flags are currently sourced.

Benchmark peer barsfor Agents

No task-mapped benchmark peers are available for this model yet.

Migration checks

No linked migration route is available for this model yet.

API versions

tencent/Hy-Memory-30B-A3BHy-Memory-30B-A3B