Task
Translation
H
shawnw3i/Hy-MT2-7B-AWQ
Translation·shawnw3i· 3.8K
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
# pull & run locally
pip install mlforge-sdk && mlforge pull shawnw3i/Hy-MT2-7B-AWQ
pip install mlforge-sdk && mlforge pull shawnw3i/Hy-MT2-7B-AWQ
Model details
Provider
shawnw3i
Framework
transformers
Parameters
7.5B
Size
4.4 GB
Downloads
3.8K
Updated
2026-05-25
About shawnw3i/Hy-MT2-7B-AWQ
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.