#OllamaAI Translate (Offline)

Ollama official website address

https://ollama.com/

Preface: This translation source is offline AI translation, you need to download Ollama software and AI offline large model

Since Ollama does not yet provide an interface, it can only be operated through the console/terminal.

If there are many users who require page operations, we will consider developing the interface. Feedback is welcome ~

AI model information As time goes by, the official website may change, this is for reference only, please refer to the official documents for details

AI Model - Official Introduction Document

Model name	Model model	Model size	Command execution
Llama 3	8B	4.7GB	ollama run llama3
Llama 3	70B	40GB	ollama run llama3:70b
Phi-3	3,8B	2.3GB	ollama run phi3
Mistral	7B	4.1GB	ollama run mistral
Neural Chat	7B	4.1GB	ollama run neural-chat
Starling	7B	4.1GB	ollama run starling-lm
Code Llama	7B	3.8GB	ollama run codellama
Llama 2 Uncensored	7B	3.8GB	ollama run llama2-uncensored
LLaVA	7B	4.5GB	ollama run llava
Gemma	2B	1.4GB	ollama run gemma:2b
Gemma	7B	4.8GB	ollama run gemma:7b
Solar	10.7B	6.1GB	ollama run solar

Prerequisites for use

Noun introduction: RAM (Random Access Memory) usually refers to the memory stick in the computer

According to the official website, the AI ​​model requires computers

7B model requires at least 8 GB of available RAM to run

13B model requires at least 16 GB of available RAM to run

33B model requires at least 32 GB of available RAM to run

We tested these three models with 24G computer memory: Gemma 2B, Llama 3 8B, llama 2 Uncensored 7B

Among them, Gemma 2B has the fastest translation speed, and the translation effect is pretty good in most cases. This is not bad if the accuracy of the translation results is not so high. For other models, the translation quality will be higher, but the speed will be reduced accordingly. You can choose according to your actual testing situation.

1. Download and install Ollama

Ollama official website:https://ollama.com/

After the installation is complete, open the computer console/terminal and enter: ollama

If the following interface appears, the installation is successful.

2. Download the AI ​​large model through Ollama

Open the computer console/terminal and copy the corresponding model command execution in the model list above

Ollama other commands

View the list of currently downloaded models

ollama list

Download model (This command can also be used to update local models. Only differences will be pulled.)

ollama pull xxx

Delete model

ollama rm xxx