Open-source AI large models such as DeepSeek and Qwen perform excellently. With the help of tools such as Ollama and LM Studio, we can easily build large model services locally and integrate them into various AI applications, such as video translation software.

However, due to the limited video memory of personal computers, locally deployed large models are usually smaller, such as 1.5B, 7B, 14B, or 32B.

The DeepSeek official online AI service uses the r1 model, which has a parameter volume of up to 671 B. This huge difference means that the intelligence of local models is relatively limited and cannot be used as casually as online models, otherwise you may encounter various strange problems, such as prompts appearing in the translation results, mixing original and translated texts, and even garbled characters.

The root cause is that small models lack intelligence and have a weak understanding and execution ability of complex prompts.

Therefore, when using local large models for video translation, you need to pay attention to the following points in order to obtain better translation results:

I. Correctly configure the API settings of the video translation software

Fill in the API address of the locally deployed model in the API interface address under the video translation software Translation Settings --> Compatible AI and Local Large Models. Usually, the API interface address should end with /v1.

• If your API interface sets an API Key, please fill it in the SK text box. If it is not set, just fill in any value, such as 1234, but do not leave it blank.
• Fill in the model name in the Fill in all available models text box. Note: Some model names may have size information, such as deepseek-r1:8b, and the suffix :8b also needs to be filled in.

II. Prioritize choosing models with larger parameters and newer versions

1. It is recommended to choose models with a parameter volume of at least 7B. If conditions permit, try to choose models larger than 14B. Of course, the larger the model, the better the effect, provided that the computer performance allows it.
2. If you are using the Tongyi Qianwen series models, prioritize choosing the qwen2.5 series instead of the 1.5 or 2.0 series.

III. Uncheck the "Send Complete Subtitles" option in the video translation software

Unless the size of the model you deployed is greater than or equal to 70B, checking "Send Complete Subtitles" may cause errors in the subtitle translation results.

IV. Reasonably set the subtitle line number parameters

Set the Traditional Translation Subtitle Line Number and AI Translation Subtitle Line Number in the video translation software to smaller values, such as 1, 5 or 10, etc. This can avoid the problem of too many blank lines and improve the reliability of the translation.

The smaller the value, the lower the possibility of translation errors, but the translation quality will also decrease; the larger the value, the better the translation quality is without errors, but it is also more prone to errors.

V. Simplify the Prompt

When the model is small, it may not be able to understand or have poor instruction compliance. At this time, you can simplify the prompt to make it simple and clear.

For example, the prompt in the default software directory/videotrans/localllm.txt file may be more complex. When you find that the translation results are not satisfactory, you can try to simplify it.

Simplified example 1:

# Role
You are a translation assistant, able to translate the text within the <INPUT> tag into {lang}.

## Requirements

- The number of lines in the translation must be equal to the number of lines in the original text
- Translate according to the literal meaning, do not explain the original text.
- Only return the translation, do not return the original text.
- If you cannot translate, please return a blank line, no apology, no explanation of the reason.

## Output format:
Directly output the translation, do not output any other prompts, such as explanations, guiding characters, etc.

<INPUT></INPUT>

Translation result:

Simplified example 2:

You are a translation assistant, translate the following text into {lang}, keep the number of lines unchanged, only return the translation, and return a blank line if you cannot translate.

Text to be translated:
<INPUT></INPUT>

Translation result:

Simplified example 3:

Translate the following text into {lang}, keeping the number of lines consistent. Leave blank if you cannot translate.

<INPUT></INPUT>

Translation result:

You can also further simplify and optimize the prompt according to the actual situation.

Through the above optimizations, even a smaller local large model can play a greater role in video translation, reduce errors, improve translation quality, and bring you a better local AI experience.