Large Language Model on windows server 2019 | support by Hfimg

AWS-Marketplace

https://aws.amazon.com/marketplace/pp/prodview-spkeiuyarjexu

Usage Instructions

*Note

To run the Llama-3.1-8B large model, EC2 instances must select g5.xlarge type, other models are selected according to requirements.

Several ways to interact with the large model

1.AI model plugged into Edge browser

Click the start deepseek.bat batch file and wait for a period of time to
automatically open the command line window and Edge browser.

To switch to another large model, right-click to edit the third line of the batch file as follows

start cmd /c "ollama run llama3.1:8b"
start cmd /c "ollama run deepseek-r1:32b"
start cmd /c "ollama run qwen3:14b"
start cmd /c "ollama run mistral"
start cmd /c"ollama run gemma3:12b"

...

2.chatbox

Basic parameters have been set, if switching large model refer to the following guide.

https://chatboxai.app/en/help-center/connect-chatbox-remote-ollama-service-guide#

3.Cherry Studio

1.Function Introduction
https://docs.cherry-ai.com/cherry-studio/preview

2.Basic parameters have been set, if switching large model refer to the following guide.
https://docs.cherry-ai.com/pre-basic/providers/ollama

3.Knowledge Base Tutorial
https://docs.cherry-ai.com/knowledge-base/knowledge-base

4.Open WebUI

Start Open WebUI

open the command line window, type open-webui serve,in the browser enter the default
access address: http://localhost:8080

5.Download and large model

- ollama run deepseek-r1:7b
- ollama run deepseek-r1:14b
- ollama run deepseek-r1:32b
- ollama run deepseek-r1:70b
- ollama run deepseek-r1:671b

- ollama run gemma3:4b
- ollama run gemma3:12b
- ollama run gemma3:27b

- ollama run llama3.1
- ollama run llama3.1:70b
- ollama run llama3.1:405b
- ollama run llama3.3

- ollama run qwen3
- ollama run qwen3:14b
- ollama run qwen3:30b
- ollama run qwen3:32b
- ollama run qwen3:235b

- ollama run mistral