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.
Alternatives to Hy-SimulMT-30B-A3B
72 open-weight models that do the same job as Hy-SimulMT-30B-A3B (30.4B translation), ranked by how close they are in task and size, then by popularity and how recent they are. Licence and VRAM are shown for each.
Compare Hy-SimulMT-30B-A3B with the top 3Hy-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 2.05.5K 520May 2026- Same category
- Similar size (30.1B vs 30.4B)
- Commercial use OK
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-license1K 31Oct 2026- Same category
- Similar size (31.8B vs 30.4B)
- Newer release
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 2.02.2K 45Sept 2026- Same category
- Smaller (9.7B vs 30.4B)
- Commercial use OK
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 2.031.4K 216May 2026- Same category
- Smaller (8B vs 30.4B)
- Commercial use OK
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-license1.6K 24Oct 2026- Same category
- Smaller (8.5B vs 30.4B)
- Newer release
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 4.02.4K 133Mar 2023- Same category
- Similar size (54B vs 30.4B)
New multilingual machine translation model (MiLMMT-46) is now available. Please check the link for detailed information.
10.2B8K ctx Gemma Terms of Use4K 79Nov 2024- Same category
- Smaller (10.2B vs 30.4B)
PLaMo Translation Model is a specialized large-scale language model developed by Preferred Networks for translation tasks. For details, please refer to the blog post and press release.
9.5B10M ctx plamo-community-license1.7K 130May 2025- Same category
- Smaller (9.5B vs 30.4B)
Hunyuan-MT-Chimera-7B-fp8 was produced by AngelSlim. The Hunyuan Translation Model comprises a translation model, Hunyuan-MT-7B, and an ensemble model, Hunyuan-MT-Chimera.
8B32K ctx Unknown licence3.5K 747Aug 2025- Same category
- Smaller (8B vs 30.4B)
We are excited to announce our official partnership with WMT26. We welcome all participants to use our HY-MT model during the competition. Teams that use HY-MT and achieve notable results will be eligible for cash prizes. For more details, please contact us at hunyuan@tencent.com.
8B256K ctx Unknown licence1.3K 162Dec 2025- Same category
- Smaller (8B vs 30.4B)
We are excited to introduce Seed-X, a powerful series of open-source multilingual translation language models, including an instruction model, a reinforcement learning model, and a reward model. It pushes the boundaries of translation capabilities within 7 billion parameters.
7.5B32K ctx openmdw2.5K 129Jul 2025- Same category
- Smaller (7.5B vs 30.4B)
- Commercial use OK
We are excited to introduce Seed-X, a powerful series of open-source multilingual translation language models, including an instruction model, a reinforcement learning model, and a reward model. It pushes the boundaries of translation capabilities within 7 billion parameters.
7.5B32K ctx openmdw997 303Jul 2025- Same category
- Smaller (7.5B vs 30.4B)
- Commercial use OK
opus-mt-en-ru is an open-weight translation model from Helsinki-NLP, published on Hugging Face.
?B512 ctx Apache 2.0589.5K 101Mar 2022- Same category
- Commercial use OK
The Hunyuan Translation Model comprises a translation model, Hunyuan-MT-7B, and an ensemble model, Hunyuan-MT-Chimera. The translation model is used to translate source text into the target language, while the ensemble model integrates multiple translation outputs to produce a higher-quality…
8B32K ctx Unknown licence294 93Aug 2025- Same category
- Smaller (8B vs 30.4B)
This model can be used for translation and text-to-text generation.
?B512 ctx CC BY 4.0387.4K 568Mar 2022- Same category
- Commercial use OK
opus-mt-de-en is an open-weight translation model from Helsinki-NLP, published on Hugging Face.
?B512 ctx Apache 2.0353.9K 50Mar 2022- Same category
- Commercial use OK
Model Description: - Developed by: Language Technology Research Group at the University of Helsinki - Model Type: Translation - Language(s): - Source Language: English - Target Language: German - License: CC-BY-4.0 - Resources for more information: - GitHub Repo
?B512 ctx CC BY 4.0287.9K 47Mar 2022- Same category
- Commercial use OK
Sarvam-Translate is an advanced translation model built by Sarvam AI in partnership with AI4Bharat, specifically designed for comprehensive, document-level translation across the 22 official Indian languages, built on Gemma3-4B-IT.
4.3B128K ctx GPL 3.065.2K 165Jun 2025- Same category
- Smaller (4.3B vs 30.4B)
- Commercial use OK
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.
2B256K ctx Apache 2.021.4K 1.3KMay 2026- Same category
- Smaller (2B vs 30.4B)
- Commercial use OK
With T5, we propose reframing all NLP tasks into a unified text-to-text-format where the input and output are always text strings, in contrast to BERT-style models that can only output either a class label or a span of the input.
61M512 ctx Apache 2.017.7M 702Mar 2022- Same category
- Smaller (61M vs 30.4B)
- Commercial use OK
- Widely used
PLaMo 3 Translate 0.8B is a translation-specialized LLM developed by Preferred Networks (PFN) that delivers world-class translation quality.
890M256K ctx plamo-community-license3.8K 50Oct 2026- Same category
- Smaller (890M vs 30.4B)
- Newer release
Index-Translate-2B is the compact 2B-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.
2.3B256K ctx Apache 2.02.1K 81Sept 2026- Same category
- Smaller (2.3B vs 30.4B)
- Commercial use OK
This is a COMET evaluation model: It receives a triplet with (source sentence, translation, reference translation) and returns a score that reflects the quality of the translation compared to both source and reference.
?BApache 2.08.7K 63Feb 2023- Same category
- Commercial use OK
With T5, we propose reframing all NLP tasks into a unified text-to-text-format where the input and output are always text strings, in contrast to BERT-style models that can only output either a class label or a span of the input.
223M512 ctx Apache 2.02.8M 811Mar 2022- Same category
- Smaller (223M vs 30.4B)
- Commercial use OK
- Widely used