Hunyuan-MT-1.5-1.8B (GGUF Quantized)

This is the GGUF quantized version of Tencent’s HY-MT1.5-1.8B translation model.

The model has been converted to Q4_K_M format using llama.cpp. This compression level offers the best balance between performance (perplexity) and resource usage, allowing the 1.8B model to run efficiently on consumer-grade hardware (requires approx. 1-2GB VRAM).

⚠️ Important Usage Note

This is an instruction-following model, not a general chatbot. It is optimized for translation tasks. Do not interact with it like ChatGPT (e.g., do not send “Hello” or “Who are you”). It works best when you provide specific translation instructions.

How to Run

ollama run demonbyron/HY-MT1.5-1.8B

🤗 Hugging Face  |   🕹️ Demo     🤖 ModelScope  |  

🖥️ Official Website  |   Github

Model Introduction

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. Among them, HY-MT1.5-7B is an upgraded version of our WMT25 championship model, optimized for explanatory translation and mixed-language scenarios, with newly added support for terminology intervention, contextual translation, and formatted translation. Despite having less than one-third the parameters of HY-MT1.5-7B, HY-MT1.5-1.8B delivers translation performance comparable to its larger counterpart, achieving both high speed and high quality. After quantization, the 1.8B model can be deployed on edge devices and support real-time translation scenarios, making it widely applicable.

Key Features and Advantages

• HY-MT1.5-1.8B achieves the industry-leading performance among models of the same size, surpassing most commercial translation APIs.
• HY-MT1.5-1.8B supports deployment on edge devices and real-time translation scenarios, offering broad applicability.
• HY-MT1.5-7B, compared to its September open-source version, has been optimized for annotated and mixed-language scenarios.
• Both models support terminology intervention, contextual translation, and formatted translation.

Related News

• 2025.12.30, we have open-sourced HY-MT1.5-1.8B and HY-MT1.5-7B on Hugging Face.
• 2025.9.1, we have open-sourced Hunyuan-MT-7B , Hunyuan-MT-Chimera-7B on Hugging Face.
  

Performance

Technical Report

 

Model Links

Prompts

Prompt Template for ZH<=>XX Translation.

将以下文本翻译为{target_language}，注意只需要输出翻译后的结果，不要额外解释：

{source_text}

Prompt Template for XX<=>XX Translation, excluding ZH<=>XX.

Translate the following segment into {target_language}, without additional explanation.

{source_text}

Prompt Template for terminology intervention.

参考下面的翻译：
{source_term} 翻译成 {target_term}

将以下文本翻译为{target_language}，注意只需要输出翻译后的结果，不要额外解释：
{source_text}

Prompt Template for contextual translation.

{context}
参考上面的信息，把下面的文本翻译成{target_language}，注意不需要翻译上文，也不要额外解释：
{source_text}

Prompt Template for formatted translation.

将以下<source></source>之间的文本翻译为中文，注意只需要输出翻译后的结果，不要额外解释，原文中的<sn></sn>标签表示标签内文本包含格式信息，需要在译文中相应的位置尽量保留该标签。输出格式为：<target>str</target>

<source>{src_text_with_format}</source>

&nbsp;

Use with transformers

First, please install transformers, recommends v4.56.0

pip install transformers==4.56.0

!!! If you want to load fp8 model with transformers, you need to change the name”ignored_layers” in config.json to “ignore” and upgrade the compressed-tensors to compressed-tensors-0.11.0.

The following code snippet shows how to use the transformers library to load and apply the model.

we use tencent/HY-MT1.5-1.8B for example

from transformers import AutoModelForCausalLM, AutoTokenizer
import os

model_name_or_path = "tencent/HY-MT1.5-1.8B"

tokenizer = AutoTokenizer.from_pretrained(model_name_or_path)
model = AutoModelForCausalLM.from_pretrained(model_name_or_path, device_map="auto")  # You may want to use bfloat16 and/or move to GPU here
messages = [
    {"role": "user", "content": "Translate the following segment into Chinese, without additional explanation.\n\nIt’s on the house."},
]
tokenized_chat = tokenizer.apply_chat_template(
    messages,
    tokenize=True,
    add_generation_prompt=False,
    return_tensors="pt"
)

outputs = model.generate(tokenized_chat.to(model.device), max_new_tokens=2048)
output_text = tokenizer.decode(outputs[0])

We recommend using the following set of parameters for inference. Note that our model does not have the default system_prompt.

{
  "top_k": 20,
  "top_p": 0.6,
  "repetition_penalty": 1.05,
  "temperature": 0.7
}

&nbsp;

Supported languages: