# Tencent releases Hy-Memory 30B-A3B under Apache 2.0

> A memory-focused mixture-of-experts model activates just 3B of its 30B parameters per token, and ships with a permissive license.

Published by The Open Weights on Oct 15, 2026. Canonical: https://theopenweights.com/news/hy-memory-30b-a3b-v5o8

## Key facts

- Company: Tencent
- Model: Hy-Memory 30B-A3B
- Version: 30B-A3B
- Category: Text / LLM
- Modalities: Text / LLM
- License: Apache 2.0 (Open weights, commercial use allowed)
- Parameters: 30B (mixture of experts)
- Active parameters: 3B
- Context window: 262K tokens
- Architecture: HYV3ForCausalLM
- Precision: BF16
- Weights size: 60.1 GB
- Significance: notable
- Published: 2026-10-15
- Last verified: 2026-10-17
- Hugging Face: https://huggingface.co/tencent/Hy-Memory-30B-A3B
- Canonical URL: https://theopenweights.com/news/hy-memory-30b-a3b-v5o8

Tencent has published Hy-Memory 30B-A3B, a text-generation language model built around a mixture-of-experts (MoE) design. According to the model's [Hugging Face repository](https://huggingface.co/tencent/Hy-Memory-30B-A3B), it carries 30 billion total parameters but activates only about 3 billion per token — the "A3B" in its name — a configuration meant to deliver the capacity of a larger model at a fraction of the inference cost.

The standout framing here is memory. As the name suggests, the model is positioned around memory-centric capabilities, a growing area of interest as developers look to build assistants that retain context across longer interactions rather than treating every exchange in isolation.

## Why it matters

Sparse MoE architectures have become the default strategy for teams trying to balance quality and serving cost, and a 30B/3B split puts Hy-Memory in a practical range for self-hosting.

- **Open license:** Apache 2.0, which permits commercial use and modification.
- **Efficient inference:** roughly 3B active parameters per token keeps compute requirements modest.
- **Focused design:** the model emphasizes memory rather than general-purpose breadth.

Tencent has steadily expanded its open-weights footprint, and an Apache-licensed release lowers the barrier for researchers and companies that want to experiment without restrictive terms. Full details on context length, benchmarks, and recommended usage are available on the [official repository](https://huggingface.co/tencent/Hy-Memory-30B-A3B).

## Get the model

- [Hugging Face](https://huggingface.co/tencent/Hy-Memory-30B-A3B)

## Sources

- [tencent/Hy-Memory-30B-A3B](https://huggingface.co/tencent/Hy-Memory-30B-A3B) — Hugging Face, Oct 15, 2026

---
Source: The Open Weights (https://theopenweights.com/). Aggregated and written by Claude, curated by humans. Cite as: "Tencent releases Hy-Memory 30B-A3B under Apache 2.0", The Open Weights, Oct 15, 2026, https://theopenweights.com/news/hy-memory-30b-a3b-v5o8