Tencent-Hunyuan/Hy-MT2
Build with Backblaze B2
SDKs, agent skills, IDE extensions, and reference pipelines from Backblaze Labs. All open source.
Loading star history...
Where it stands
Rank, growth pace and release cadence relative to everything GStars tracks.
The project lists 2 contributors on GitHub.
Peaked at #98 in the weekly ranking the week of Oct 11, its best in the past year.
Use Cases & Benefits
- Provides a family of fast-thinking multilingual translation models supporting 33 languages with sizes from 1.8B to 30B parameters.
- Delivers outstanding translation quality with efficient on-device deployment via extreme quantization reducing model size and improving speed.
- Use for integrating high-quality multilingual translation in real-world business applications requiring instruction-following capabilities.
- Use for deploying lightweight translation models on edge devices with limited storage and compute resources using AngelSlim quantization.
- Use for benchmarking and research on translation instruction-following using the open-sourced IFMTBench evaluation suite.
Should you depend on it?
License terms, project hygiene and risks, from GitHub metadata and GStars' snapshots.
License
Other
GitHub could not identify this license; read the LICENSE file before depending on it.
Community files
- README: present
Watch-outs
- License not identified by GitHub; read the LICENSE file before depending on it.
- No GitHub releases; pin a commit or tag instead of a release.
General guidance from repository metadata, not legal advice. How we score
From the README
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. For on-device deployment, AngelSlim 1.25-bit extreme quantization reduces the storage requirement of the 1.8B model to only 440 MB and improves inference speed by 1.5x. Multi-dimensional evaluations show that Hy-MT2 delivers outstanding performance across general, real-world business, domain-specific, and instruction-following translation tasks. The 7B and 30B-A3B models outperform open-source models such as DeepSeek-V4-Pro and Kimi K2.6 in fast-thinking mode, while the lightweight 1.8B model also surpasses mainstream commercial APIs from providers such as Microsoft and Doubao overall.
In this release, we also open-source IFMTBench, a benchmark for evaluating translation instruction-following capabilities.
We also welcome everyone to use our released Hy-MT2-Translator Skill, which makes it easy to integrate Hy-MT2 series models for translation tasks. Download links: ClawHub and SkillHub.
Daily snapshots
Stars gained per day, and how forks and open issues moved, from GStars' daily snapshots
+330 stars over 19 days across 4 snapshot days; best day +24 on Oct 10.
Forks
159+45
Open issues
14+0
Compared with peers in Backend
Fastest-growing repositories GStars tracks in this cohort for the week of Nov 1, by 7-day star growth
| Repository | Stars | +7d | Health | Last release |
|---|---|---|---|---|
| anthropics/skills | 187.8K | +2.9K | 15 | — |
| DuarteSantos8/openGym | 19.7K | +2.4K | 60 | 2 days ago |
| shiyu-coder/Kronos | 47.0K | +2.3K | 16 | — |
| NationalSecurityAgency/ghidra | 98.2K | +2.3K | 64 | 14 days ago |
| microsoft/VibeVoice | 56.0K | +1.1K | 29 | — |
| Tencent-Hunyuan/Hy-MT2 | 1.5K | — | 6 | — |
| Category median | 56.0K | +2.3K | 29 | — |
Also by Tencent-Hunyuan
Other repositories from this maintainer that GStars tracks
Discover Repositories
Search across tracked repositories by name or description