---
type: "post"
id: "tencent-hunyuan-open-sources-hy-simulmt-a-30b-fd28ee"
slug: "tencent-hunyuan-open-sources-hy-simulmt-a-30b-fd28ee"
title: "Tencent Hunyuan open-sources Hy-SimulMT, a 30B-A3B real-time Chinese-English simultaneous speech translation model"
description: "Tencent Hunyuan has released Hy-SimulMT-30B-A3B on Hugging Face under the Apache 2.0 licence."
retrieval_nugget: "Tencent Hunyuan has released Hy-SimulMT-30B-A3B on Hugging Face under the Apache 2.0 licence."
published_at: "2026-10-26"
updated_at: "2026-10-26"
record_date: "2026-10-26"
date_kind: "published_at"
topics: ["open-models","multimodal"]
entities: ["Tencent Hunyuan","Hy-SimulMT-30B-A3B","SimulInfer","SimulTrain","Hugging Face","llama.cpp"]
related_patterns: []
novelty_label: "new_fact"
what_changed: "Tencent Hunyuan adds Hy-SimulMT, a 30B-A3B open-weight model for real-time Chinese-English simultaneous speech translation."
prior_refs: ["memory:033209b9-0b93-8361-a395-a907c5e5e1ef","memory:591a1969-0ba9-8341-a9df-eadd57cc0d7a"]
source_url: "https://huggingface.co/tencent/Hy-SimulMT-30B-A3B"
source_urls: ["https://huggingface.co/tencent/Hy-SimulMT-30B-A3B"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:tencent-hunyuan-open-sources-hy-simulmt-a-30b-fd28ee"
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/posts/tencent-hunyuan-open-sources-hy-simulmt-a-30b-fd28ee/","markdown":"https://newruntime.com/posts/tencent-hunyuan-open-sources-hy-simulmt-a-30b-fd28ee.md","json":"https://newruntime.com/posts/tencent-hunyuan-open-sources-hy-simulmt-a-30b-fd28ee.json"}
---

# Tencent Hunyuan open-sources Hy-SimulMT, a 30B-A3B real-time Chinese-English simultaneous speech translation model

## Retrieval answer

Tencent Hunyuan has released Hy-SimulMT-30B-A3B on Hugging Face under the Apache 2.0 licence.

Tencent Hunyuan has released Hy-SimulMT-30B-A3B on Hugging Face under the Apache 2.0 licence. The model is a mixture-of-experts system with 30 billion total parameters and about 3 billion active parameters.

Hy-SimulMT is designed for bidirectional Chinese-English simultaneous speech translation: it takes a continuous audio stream while a speaker is still talking and produces translated text. Tencent says a separately configured TTS service can produce translated speech with real-time voice cloning. The release includes BF16, FP8, and GGUF weights, an Interleave variant, the SimulInfer inference service, and SimulTrain training tools.

Tencent reports about three seconds of StreamLAAL lag on the RealSI long-form benchmark, plus a GEMBA score above the open-source systems and four of five commercial APIs it compared. Those are vendor-reported comparisons; the source does not establish independent benchmark results, production reliability, TTS quality, or upstream llama.cpp support. The model card says llama.cpp support has not yet been merged upstream.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Open Models](https://newruntime.com/topics/open-models.md): Explore the open-models topic hub.
- topic hub: [Multimodal](https://newruntime.com/topics/multimodal.md): Explore the multimodal topic hub.
- collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)