Dreamsavior

Using Sugoi LLM with Translator++ (Patreon)

Published:

2025-06-25 05:27:27

Edited:

2025-06-25 05:27:34

Imported:

2026-06

Tags:

ChatGPT OpenAI Sugoi Japanese Translator Translator++

Content

Fellow translators,

I've just uploaded a new tutorial that shows how to connect Translator++ with the new Sugoi LLM model. A few of you have been asking about this, so I wanted to put together a straightforward guide.

You can watch the video here:https://youtu.be/NBsVaSqVQ-4

The video walks through the whole process using LM Studio, which is a tool for running these kinds of AI models on your own computer.

A nice side effect of this is that the OpenAI Chat add-on can now be used for any LLM that LM Studio supports. So, even though the tutorial uses Sugoi as the example, you can follow the same steps for models like Llama, DeepSeek, and others.

This setup is great if you want to keep your translations private and off the cloud, or if you just want to experiment with different local models without needing an API key.

Hope you find it helpful! Let me know if you have any questions or feedback in the comments.

As always, thank you for your support. It makes a huge difference.

Happy translating,

Dreamsavior

Files

How to Use Sugoi LLM (or any LLM) in Translator++ with LM Studio

Unlock the power of local and private AI for your translation projects! This step-by-step tutorial shows you how to integrate any local Large Language Model (LLM) with Translator++ using the incredible LM Studio. In this guide, we use the "Sugoi 14b" model as an example, but the method shown here works for virtually any LLM that can be run through LM Studio, including models like Llama, DeepSeek, Gemma, and more. The key is LM Studio's ability to create a local server that is compatible with the OpenAI Chat API. This allows you to use the versatile "OpenAI Chat" add-on in Translator++ to send translation requests to your own computer, ensuring privacy and potentially cutting costs. What you'll learn in this video: (0:00) How to download and install your chosen LLM model for LM Studio. (0:10) Setting up the model within LM Studio and finding the correct folder. (1:08) Loading the model and starting the local OpenAI-compatible server. (1:28) Finding your local server URL (e.g., http://127.0.0.1:1234). (1:40) Configuring the "OpenAI Chat" add-on in Translator++ to connect to your local AI. (2:15) Important settings to consider, as local models can be sensitive to too many concurrent requests. (2:33) Running a batch translation using your own local AI! This setup is perfect for translators who want more control over their tools, need to work offline, or wish to experiment with specialized LLMs for their projects. Important Notes: Translation speed is highly dependent on your GPU's power and VRAM. Local models may require tweaking settings like "Max concurrent requests" for best performance. Links: Translator++: https://dreamsavior.net LM Studio: https://lmstudio.ai/ Support the Translator++ Project on Patreon: https://www.patreon.com/dreamsavior Sugoi toolkit: https://sugoitoolkit.com/ Thanks for watching! If you found this guide helpful, please leave a like, subscribe for more tutorials, and let us know in the comments what models you're using!