selfhost.directory

The index of self-hostable projects — ranked, categorized and served with live updates.
Own your data and stop giving it to big tech.

tencent logo

Hy-SimulMT-30B-A3B

tencent·Base model·released 22 Oct 2026

Apache 2.030.4BA3BMoE256K ctx ≈37 GB
Your GPU
hf download tencent/Hy-SimulMT-30B-A3B
Setup ↓

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.

How much VRAM does Hy-SimulMT-30B-A3B need?

At Q8_0 Hy-SimulMT-30B-A3B needs about 37 GB of GPU memory.

--vram
any
--gpus
--quant
QuantisationWeightsTotal
4-bitRecommended default for local use17 GB ≈21 GB
8-bitrecommendedLossless in practice, twice the size of Q430 GB ≈37 GB
FP16 / BF16Full precision, as released57 GB ≈68 GB

Estimates for the weights plus runtime overhead; activations vary with resolution and batch size. Pick a GPU above and the fit column checks every row against it.

Can the Tesla P40 run Hy-SimulMT-30B-A3B? →

Run Hy-SimulMT-30B-A3B locally

These commands load the original weights from Hugging Face.

Run with the translation pipelinedocs
python
from transformers import pipeline

pipe = pipeline("translation", model="tencent/Hy-SimulMT-30B-A3B")
result = pipe("Self-hosting puts you in control of your data.")
print(result)

Install Transformers

About 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. 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

Full model card on Hugging Face →

Alternatives to Hy-SimulMT-30B-A3B

All alternatives →
tencent logo

Hy-MT2-30B-A3B

tencent·Translation

≈36 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.

30.1BA3B256K ctx Apache 2.0
5.4KMay 2026gguf
pfnet logo

plamo-3-translate-31b

pfnet·Translation

≈38 GB

PLaMo 3 Translate 31B is a translation-specialized LLM developed by Preferred Networks (PFN) that delivers world-class translation quality.

31.8B256K ctx plamo-community-license
949Oct 2026gguf
IndexTeam logo

Index-Translate-9B

IndexTeam·Translation

≈12 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.

9.7B256K ctx Apache 2.0
2.2KSept 2026gguf
tencent logo

Hy-MT2-7B

tencent·Translation

≈10 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.

8B256K ctx Apache 2.0
31.1KMay 2026gguf
pfnet logo

plamo-3-translate-8b

pfnet·Translation

≈11 GB

PLaMo 3 Translate 8B is a translation-specialized LLM developed by Preferred Networks (PFN) that delivers world-class translation quality.

8.5B256K ctx plamo-community-license
1.5KOct 2026gguf
facebook logo

nllb-moe-54b

facebook·Translation

≈65 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…

54B1K ctx CC BY-NC 4.0
2.4KMar 2023

Hy-SimulMT-30B-A3B 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.

Data from Hugging Face, the model card and public leaderboards. Memory and speed figures are estimates; real numbers depend on the runtime, context length and drivers. Always check the licence yourself before commercial use.