A new collection of open translation models built on Gemma 3, helping people communicate across 55 languages.
1.6M Pulls 13 Tags Updated 4 months ago
A state-of-the-art 12B model with 128k context length, built by Mistral AI in collaboration with NVIDIA.
4.8M Pulls 17 Tags Updated 10 months ago
HY-MT2 1.8B, 7B, and 30B-A3B (MoE) multilingual translation models designed for complex real-world scenarios, it supports translation among 33 languages and effectively follows translation instructions.
336 Pulls 7 Tags Updated 6 days ago
Fine-tuned Gemma 4 E4B for quality-checking Bethesda/Starfield game string translations. Detects 16 issue codes: tag mismatches, source-language leak, English leak, AI artifacts, repetition, truncation, and more.
1 Pull 1 Tag Updated 11 hours ago
Uncensored, non-thinking Qwen3.5 tuned for pure translation — input text, output translation, nothing else.
273 Pulls 1 Tag Updated 1 week ago
Hy-MT2 is a family of “fast-thinking” multilingual translation models designed for complex real-world scenarios.
201 Pulls 1 Tag Updated 1 week ago
An optimized version of Google's TranslateGemma-12B-it (Gemma 3) designed for high-fidelity translation. This build features hard-coded Temperature=0.1 and English Anchor support to eliminate output redundancy and maximize accuracy.
33.8K Pulls 1 Tag Updated 4 months ago
Hunyuan Translation Model Version 1.5 includes a 1.8B translation model, HY-MT1.5-1.8B, and a 7B translation mode
11.6K Pulls 16 Tags Updated 5 months ago
Tencent's state-of-the-art Hunyuan-MT-1.5-1.8B translation model, quantized to Q4_K_M GGUF. Supports 33 languages with specialized handling for mixed-language and explanatory translation. Optimized for instruction-following.
3,329 Pulls 3 Tags Updated 4 months ago
Tencent's state-of-the-art Hunyuan-MT-1.5-7B translation model, quantized to Q4_K_M GGUF. Supports 33 languages with specialized handling for mixed-language and explanatory translation. Optimized for instruction-following.
2,268 Pulls 2 Tags Updated 4 months ago
Hunyuan Translation Model Version 1.5 includes a 1.8B translation model, HY-MT1.5-1.8B, and a 7B translation model, HY-MT1.5-7B. Both models focus on supporting mutual translation across 33 languages and incorporating 5 ethnic and dialect variations.
1,455 Pulls 5 Tags Updated 4 months ago
Tencent's state-of-the-art Hunyuan translation model in 1.8B and 7B sizes. Supports 33 languages with specialized capabilities for terminology intervention, contextual awareness, and formatted text translation.
1,150 Pulls 3 Tags Updated 4 months ago
TranslateGemma is a family of lightweight, state-of-the-art open translation models from Google, based on the Gemma 3 family of models. TranslateGemma models are designed to handle translation tasks across 55 languages.
773 Pulls 12 Tags Updated 4 months ago
Hunyuan Translation Model Version 1.5 includes a 1.8B translation model. The 1.8B model can be deployed on edge devices and support real-time translation scenarios, making it widely applicable.
336 Pulls 3 Tags Updated 4 months ago
Hunyuan Translation Model Version 1.5
252 Pulls 2 Tags Updated 4 months ago
Hunyuan Translation Model Version 1.5(HY-MT)
166 Pulls 7 Tags Updated 4 months ago
Tencent's state-of-the-art Hunyuan-MT-1.5-1.8B translation model, quantized to Q8_0 GGUF. Supports 33 languages with specialized handling for mixed-language and explanatory translation. Optimized for instruction-following.
150 Pulls 1 Tag Updated 4 months ago
Isolate the response only for translation purposes
115 Pulls 1 Tag Updated 3 months ago
72 Pulls 3 Tags Updated 4 months ago
The Hunyuan Translation Model comprises a translation model, Hunyuan-MT-7B, and an ensemble model, Hunyuan-MT-Chimera.
7,788 Pulls 9 Tags Updated 9 months ago