# Hy-SimulMT-30B-A3B

> Hy-SimulMT is a real-time simultaneous translation model developed by Tencent Hunyuan, supporting bidirectional speech-to-speech translation between Chinese and English. It continuously receives incoming audio and translates as the speaker talks, producing both translated text and speech.

- **Organisation:** tencent
- **Category:** Translation
- **Parameters:** 30.4B total, 3B active (MoE)
- **Context length:** 262,144 tokens
- **Licence:** Apache 2.0 (Commercial use OK)
- **Released:** 2026-10-22
- **Hugging Face:** 1.3K downloads (30 days), 50 likes

## Estimated memory

| Quant | ≈ GB |
|---|---|
| Q4_K_M | 21.09 |
| Q8_0 | 36.59 |
| F16 | 68.44 |

## Runs with

- [Transformers](https://github.com/huggingface/transformers)

## About

Hy-SimulMT is a real-time simultaneous translation model developed by Tencent Hunyuan, supporting bidirectional speech-to-speech translation between Chinese and English. It continuously receives incoming audio and translates as the speaker talks, producing both translated text and speech. With real-time voice cloning, it preserves the speaker's vocal characteristics while conveying the message accurately.

Designed for live communication settings such as meetings, speeches, and interviews, Hy-SimulMT aims to convey information accurately while reducing the disruption that waiting introduces into a conversation. To evaluate this balance between translation quality and response speed, we combine public benchmarks, real-world audio, and comparisons with professional simultaneous interpreters.

In our RealSI long-form audio evaluation, Hy-SimulMT achieved a StreamLAAL of approximately 3 seconds, the lowest among the systems shown in the comparison. Its GEMBA score exceeded those of the compared open-source models and four of the five commercial APIs.

The GitHub repository provides the SimulInfer inference service and SimulTrain training tools. Speech output and voice cloning require a configured TTS service. You can also try Hy-SimulMT in the Hy Translate App.

Scan to download the Hy Translate App

## Alternatives

- [tencent/Hy-MT2-30B-A3B](https://selfhost.directory/models/tencent/hy-mt2-30b-a3b) (30.1B (3B active), Apache 2.0, ≈36.2 GB): Hy-MT2 is a family of “fast-thinking” multilingual translation models designed for complex real-world scenarios. It includes three model sizes: 1.8B, 7B, and 30B-A3B (MoE), all of which support translation among 33 languages and effectively follow translation instructions in multiple languages.
- [pfnet/plamo-3-translate-31b](https://selfhost.directory/models/pfnet/plamo-3-translate-31b) (31.8B, plamo-community-license, ≈38.21 GB): PLaMo 3 Translate 31B is a translation-specialized LLM developed by Preferred Networks (PFN) that delivers world-class translation quality.
- [IndexTeam/Index-Translate-9B](https://selfhost.directory/models/indexteam/index-translate-9b) (9.7B, Apache 2.0, ≈11.96 GB): Index-Translate-9B is the 9B-parameter multilingual text model of the Index-Translate family, built on Qwen3.5. It supports text translation across 150 languages and follows translation instructions involving terminology, formatting, style, structure, context, and output length.
- [tencent/Hy-MT2-7B](https://selfhost.directory/models/tencent/hy-mt2-7b) (8B, Apache 2.0, ≈10.03 GB): Hy-MT2 is a family of “fast-thinking” multilingual translation models designed for complex real-world scenarios. It includes three model sizes: 1.8B, 7B, and 30B-A3B (MoE), all of which support translation among 33 languages and effectively follow translation instructions in multiple languages.
- [pfnet/plamo-3-translate-8b](https://selfhost.directory/models/pfnet/plamo-3-translate-8b) (8.5B, plamo-community-license, ≈10.63 GB): PLaMo 3 Translate 8B is a translation-specialized LLM developed by Preferred Networks (PFN) that delivers world-class translation quality.
- [facebook/nllb-moe-54b](https://selfhost.directory/models/facebook/nllb-moe-54b) (54B, CC BY-NC 4.0, ≈64.62 GB): The NLLB model was presented in No Language Left Behind: Scaling Human-Centered Machine Translation by Marta R. Costa-jussà, James Cross, Onur Çelebi, Maha Elbayad, Kenneth Heafield, Kevin Heffernan, Elahe Kalbassi, Janice Lam, Daniel Licht, Jean Maillard, Anna Sun, Skyler Wang, Guillaume Wenzek…

More: https://selfhost.directory/models/tencent/hy-simulmt-30b-a3b/alternatives

## Runs well on

- [Tesla P40](https://selfhost.directory/models/tencent/hy-simulmt-30b-a3b/on/tesla-p40): Q4_K_M
- [Radeon RX 7900 XTX](https://selfhost.directory/models/tencent/hy-simulmt-30b-a3b/on/rx-7900-xtx): Q4_K_M
- [Instinct MI50 32GB](https://selfhost.directory/models/tencent/hy-simulmt-30b-a3b/on/instinct-mi50): Q4_K_M
- [GeForce RTX 5090](https://selfhost.directory/models/tencent/hy-simulmt-30b-a3b/on/rtx-5090): Q4_K_M
- [Apple M4 Pro (48 GB)](https://selfhost.directory/models/tencent/hy-simulmt-30b-a3b/on/apple-m4-pro-48gb): Q4_K_M
- [RTX A6000](https://selfhost.directory/models/tencent/hy-simulmt-30b-a3b/on/rtx-a6000): Q8_0

## Similar size

- [tencent/Hy-MT2-30B-A3B](https://selfhost.directory/models/tencent/hy-mt2-30b-a3b) (30.1B)
- [pfnet/plamo-3-translate-31b](https://selfhost.directory/models/pfnet/plamo-3-translate-31b) (31.8B)

## FAQ

**How much VRAM does Hy-SimulMT-30B-A3B need?**
About 37 GB at Q8_0. Full precision needs about 68 GB.

**Can Hy-SimulMT-30B-A3B run on the Tesla P40?**
Yes. It fits at Q4_K_M (about 21 GB). It fits comfortably on the Radeon RX 7900 XTX, Instinct MI50 32GB, RTX 5090.

**Can I use Hy-SimulMT-30B-A3B commercially?**
Yes. It is released under Apache 2.0. Permissive: use, modify and sell freely; keep the notice and licence text.

**How do I run Hy-SimulMT-30B-A3B locally?**
It runs with Transformers. Each has copy-paste examples in its docs.

## Links

- huggingface: https://huggingface.co/tencent/Hy-SimulMT-30B-A3B
- github: https://github.com/Tencent-Hunyuan/Hy-SimulMT

---
Source: https://selfhost.directory/models/tencent/hy-simulmt-30b-a3b