Home
Creators
Search Recent Random
Posts
Search DMs Popular Hash Lookup Tags Random
Importer
Import FAQ
Register Favorites Keys Review DMs Logout
Community
Telegram ThePornDude
Home Creators Posts Import Register Favorites Logout

1-Click INSTALL LOCAL TEXT GEN WebUI! (Patreon)

Published:
2025-11-08 18:41:40
Edited:
2026-03-26 17:03:16
Imported:
2026-06
Tags:

Downloads

Content

Hey everyone! I've created a 1-click installer for the Oobabooga TextGen WebUI 2025 Update, the easiest way to run your favorite open-source LLMs locally for FREE! This version is a massive improvement over the old one, with faster installs, full model compatibility, and a cleaner interface that makes it easier than ever to use.You can check out the video right here: https://youtu.be/QSJS9YDqf9wThe installer of course automates the entire install process for the webui!Links for the models:CYDONIA 24B: bartowski/TheDrummer_Cydonia-24B-v4.1-GGUF · Hugging FaceGPT-OSS-120B: unsloth/gpt-oss-120b-GGUF · Hugging FaceGLM-4.5-355B: unsloth/GLM-4.5-GGUF · Hugging FaceGLM-4.5-Air-106B: unsloth/GLM-4.5-Air-GGUF · Hugging Face

LOCAL INSTALL

Download the TEXT-GEN_WEBUI_INSTALLER.bat

Run the bat file

It will then asks which GPU you got, most of you will choose A for Nvidia, since other GPUs are only really compatible on Linux (like AMD) press enter

Wait for the install to finish

The webui will launch, or hold ctrl then left click on the local url and there you go😎

IF YOU ARE USING RUNPOD :

Create an account if you haven't already: Runpod

Click on Pod (on the left side) then click deploy

Choose a GPU OR GPUs, depending on what you are looking for, chose the pytorch 2.8.0, then edit the template and choose min 300gb for both the container and volume disk, add the 7860 port and then deploy on demand

Go to my pods, wait for everything to finish and then click "connect", then "Connect to HTTP SERVICE port 8888" and drag and drop the TEXT-GEN_WEBUI_INSTALL-RUNPOD.sh file on the left side of the UI then click on the "Terminal" icon on the right side on the UI

Copy and paste these two lines then press enter:

chmod +x TEXT-GEN_WEBUI_INSTALL-RUNPOD.sh

./TEXT-GEN_WEBUI_INSTALL-RUNPOD.sh start

Choose if you want to put a username and passwordWait for everything to be installed

Go to the port 7860 and there you go 😎IF YOU PAUSE THE POD THEN RESTART IT AND YOU WANT TO RESTART THE WEBUI:click on the terminal icon and there type:./start_linux.sh --listen --listen-host 0.0.0.0 --listen-port 7860 --gradio-auth user:passwhere user:pass is your username and passwordIF YOU NEED TO DOWNLOAD A BIG MODELGo inside the text generation webui folder, drag and drop the MODEL_DOWNLOADER-RUNPOD.sh file on the left side of the UI then click on the "Terminal" icon on the right side on the UI

Copy and paste these two lines then press enter:

chmod +x MODEL_DOWNLOADER-RUNPOD.sh

./MODEL_DOWNLOADER-RUNPOD.shIt will then ask you to paste the url of the model from huggingface and once you do, press enter and it will dl quickly all the model files.

As always, supporting me on Patreon allows me to keep creating helpful resources like this for the community. Thank you for your support - now go have some fun😉!PS: Sorry again for the lack of communication, those who know, knows ❤️

Files

Comments

H-BOX

I'm using an API of gemini 2.5 on RisuAi... I really don't think LLM can get to it's ankle in terms of experience. Is it really smarter even if you run on a regular machine ?

Aitrepreneur

You'll get gonna get a model smarter than a huge LLM running on a consumer grade gpu, but there are models are rivals or even often surpasses models like chatgpt, as long as you got enough vram

H-BOX

Really ?? Gotta try that on a rental gpu at least to have an idea.. merci !

TP

I'm getting the following error when running your bat file: ******************************************************************* * You haven't downloaded any model yet. * Once the web UI launches, head over to the "Model" tab and download one. ******************************************************************* Traceback (most recent call last): File "E:\LocalTextGen\text-generation-webui\server.py", line 6, in from modules import shared File "E:\LocalTextGen\text-generation-webui\modules\shared.py", line 9, in import yaml ModuleNotFoundError: No module named 'yaml' Press any key to continue . . . Could you please help me solve this?

E Farts

Just curious, you might mention it in the video, but you use Oobabooga in this install. What are your thoughts on using it over Silly Tavern? (That's my usual go to.) I'm still learning about LLMs, so I don't know the difference.

marly.ai

I used the same name as the video tutorial folder “TXTGEN” without spaces, and this error message appears for me. [This script relies on Miniforge which can not be silently installed under a path with spaces. Press any key to continue . . .]

Virtamouse

The local installer does not ask me what GPU I have. It just starts installing instantly. and I get the following error. ╭───────────────────────────────────────── Traceback (most recent call last) ──────────────────────────────────────────╮ │ M:\LocalTXT\text-generation-webui\server.py:7 in │ │ │ │ 6 from modules import shared │ │ ❱ 7 from modules.block_requests import OpenMonkeyPatch, RequestBlocker │ │ 8 from modules.logging_colors import logger │ │ │ │ M:\LocalTXT\text-generation-webui\modules\block_requests.py:7 in │ │ │ │ 6 │ │ ❱ 7 from modules import shared, ui │ │ 8 from modules.logging_colors import logger │ │ │ │ M:\LocalTXT\text-generation-webui\modules\ui.py:67 in │ │ │ │ 66 if not shared.args.old_colors: │ │ ❱ 67 theme = theme.set( │ │ 68 # General Colors │ ╰──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯ TypeError: Base.set() got an unexpected keyword argument 'button_shadow_hover' Press any key to continue . . .

Julien Natter

Be sure to not execute as administrator, otherwise it will try to find Miniforge in system32 instead of the current folder you're in

E Farts

Yeah I got a similar error. Although mine said it couldn't find a module called "rich". I'm running the update wizard and seeing if that fixes it. Will let you know.

Aitrepreneur

Try running the update wizard file as E farts said, first, if not, you can dm

Aitrepreneur

Sillytavern is gonna be for the next video ;)

Aitrepreneur

make sure to run the installer in a folder without spaces in the names so if you got something like C:\Users\username\AI TOOLS\AI that's not gonna work because AI TOOLS has a space in the name

Aitrepreneur

Never seen this error before... are you running it normally and not as admin?

Jaiven

Oh thank god, I love Sillytavern.

Jaiven

Getting this error * Installing PyTorch. ******************************************************************* CondaToSNonInteractiveError: Terms of Service have not been accepted for the following channels. Please accept or remove them before proceeding: - https://repo.anaconda.com/pkgs/main - https://repo.anaconda.com/pkgs/r - https://repo.anaconda.com/pkgs/msys2 To accept these channels' Terms of Service, run the following commands: conda tos accept --override-channels --channel https://repo.anaconda.com/pkgs/main conda tos accept --override-channels --channel https://repo.anaconda.com/pkgs/r conda tos accept --override-channels --channel https://repo.anaconda.com/pkgs/msys2 For information on safely removing channels from your conda configuration, please see the official documentation: https://www.anaconda.com/docs/tools/working-with-conda/channels Command '"D:\AI\Text-GEN\text-generation-webui\installer_files\conda\condabin\conda.bat" activate "D:\AI\Text-GEN\text-generation-webui\installer_files\env" >nul && conda install -y ninja git && python -m pip install torch==2.7.1 --index-url https://download.pytorch.org/whl/cu128 && python -m pip install py-cpuinfo==9.0.0' failed with exit status code '1'. Exiting now. Try running the start/update script again. Press any key to continue . . .

Forest

I'm getting the same error. Running it like normal. It doesn't ask GPU, either

DanO..

Where can I get the mmproj file for Cydonia so I can run it multimodal (vision)? Or is that not something that will work?

Forest

I was able to go into the folder and choose "update_wazzard_windows.bat" it updated. I was able to choose my GPU, etc.. Next it asked me to update extention. I exited out at that point

Virtamouse

I did that also, but when I download a model I get another error, Unable to load model.

E Farts

Aaahhhh. ☞(¬‿¬)☞

Virtamouse

Traceback (most recent call last): File "M:\LocalTXT\text-generation-webui\modules\ui_model_menu.py", line 204, in load_model_wrapper shared.model, shared.tokenizer = load_model(selected_model, loader) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "M:\LocalTXT\text-generation-webui\modules\models.py", line 43, in load_model output = load_func_map[loader](model_name) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "M:\LocalTXT\text-generation-webui\modules\models.py", line 71, in llama_cpp_server_loader from modules.llama_cpp_server import LlamaServer File "M:\LocalTXT\text-generation-webui\modules\llama_cpp_server.py", line 13, in import llama_cpp_binaries ModuleNotFoundError: No module named 'llama_cpp_binaries'

Intrenxic Dark

I'm getting this error too and nothing is working

E Farts

Make sure to DM AItrepreneur. It helps them troubleshoot easier. Also, make sure to list your computer specs. It helps.

Yukon Cornelius

Hey folks. I had some trouble as well but I think it was my own fault. The install seems to take only 30-60 seconds. BUT, then you must go into the new folder and run the update.bat or whatever its called. make sure to update the ui, and dependencies. seems to be running fine now. I just need to download a model next. EDIT: nevermind. I got the model downloaded and have entered some sort of endless fresh hell that keeps making me install gradio and complains about the python version im using and some other stuff so. idk what the answer is, lol. EDIT: Finally got it working. I ended up having to edit the 'start_windows.bat' file so that it looked specifically for python 3.13. idk why but that worked. everything else was a clusterf**k

Forest

Yep, Same

Elkin Marenco

Ok I had the same problem and this works for me: Go to your oobabooga folder on a windows command window (not powershell) in my case is F:\AI\OOBABOOGA\aitrepeneur\text-generation-webui Run to avoid system Python installer_files\env\python.exe -V installer_files\env\python.exe -m pip install --upgrade pip Install the requirements , full or portable in my case is portable installer_files\env\python.exe -m pip install -r requirements\portable\requirements.txt for full is installer_files\env\python.exe -m pip install -r requirements\full\requirements.txt I launched the UI with installer_files\env\python.exe server.py --api --auto-launch

Virtamouse

Im seeing this now when I start the tool. It starts but I am unable to load the model. A module that was compiled using NumPy 1.x cannot be run in NumPy 2.2.6 as it may crash. To support both 1.x and 2.x versions of NumPy, modules must be compiled with NumPy 2.0. Some module may need to rebuild instead e.g. with 'pybind11>=2.12'.

Virtamouse

This was the solution that worked for me. I tried everything else. After following your guide I loaded the webui and loaded the model successfully.

Virtamouse

This is the fix for those having errors or unable to load the model. From user Elkin Marenco · 44min Ok I had the same problem and this works for me: Go to your oobabooga folder on a windows command window (not powershell) in my case is F:\AI\OOBABOOGA\aitrepeneur\text-generation-webui Run to avoid system Python installer_files\env\python.exe -V installer_files\env\python.exe -m pip install --upgrade pip Install the requirements , full or portable in my case is portable installer_files\env\python.exe -m pip install -r requirements\portable\requirements.txt for full is installer_files\env\python.exe -m pip install -r requirements\full\requirements.txt I launched the UI with installer_files\env\python.exe server.py --api --auto-launch

Manu

I was get same error like you. I create folder in C but somehow dont like that. Now i do other folder in E also folder Name is like: E:\GenWebUI\ dont do E:\Gen WebUI\ ..And for me was fix the problem.

newtoai

Thanks! It installed perfectly and with zero issues for me on a 5090 nvidia card machine :-)

Taiga

Traceback (most recent call last): File "D:\TEXT_GEN\text-generation-webui\server.py", line 6, in from modules import shared File "D:\TEXT_GEN\text-generation-webui\modules\shared.py", line 11, in from modules.logging_colors import logger File "D:\TEXT_GEN\text-generation-webui\modules\logging_colors.py", line 67, in setup_logging() File "D:\TEXT_GEN\text-generation-webui\modules\logging_colors.py", line 30, in setup_logging from rich.console import Console ModuleNotFoundError: No module named 'rich'

TP

Thank you all for replies! Elkins method worked :-)

Julien Schittenhelm

Downloaded the the Web UI installer bat. Tried to run it. Computer asks me if I want to install it, then nothing...

Cristo

I selected 2 RTX 6000 PRO GPUS and this is the error I got while it was installing the file: Transaction finished installation finished. Miniforge version: conda 25.3.0 Channels: - conda-forge Platform: linux-64 Collecting package metadata (repodata.json): failed CondaHTTPError: HTTP 000 CONNECTION FAILED for url Elapsed: - An HTTP error occurred when trying to retrieve this URL. HTTP errors are often intermittent, and a simple retry will get you on your way. 'https//conda.anaconda.org/conda-forge/noarch' Conda environment is empty.

Screamingiraffe

What about a 1-click install for vllm using wsl, to make use of the VL and Thinking Qwen3 models. LM Studio and OogaBooga do not support either.

William McDonald

So this has it running locally on the single device, how do I make it connectable, so I can enter the address and access it on my other 2 computers, using the main one as a server?

CodeCrafters Collective

normally when an app running the start command change from 127.0.0.1 to 0.0.0.0 and it will be availible on your local network as long as no firewall rules are blocking it.

Onyx N

how to open it after im done installing? i mean not from the installer

Ken L. Black

Looking forward to the promised next video on this to see more about chatting, etc. Do you (or anyone) have recommendations for where to find additional characters? Can I create my own within this web interface? (I'm new to this, obviously.....)

Justin Berken

Can these models run in LM studio or Ollama.cpp?

J

Thank you for the video.

Hrothgar's Hoard

Anyone have suggestions on models to use? I'm trying the TheDrummer_Cydonia-24B-v4.1-Q6_K_L.gguf and it works well enough, but it seems *really* chatty. I'll ask a 3 word question and I get multiple paragraphs in response.

HEX

does this work on mac

Jez

played around with various TTs extensions... Piper TTS seems a good choice for quality and speed (5090)

Ian Solo

I tried cidonia it is very weak compared to chatGPT. It can't answer most specific questions as chatGPT does.Also it not unscensored. I asked a question about blackhat ad on IG for instance and it answered the usual "i can only talk about legit methods bla bla bla". Also it is quite slow even with a 5090. Well not worth it.

Kodaijin Starfall

How does one accept the conta tos and eula when using the 1-click bat file?

Teresa Greasley

Will there be updates to this? If so will they be posted here or on Hugging Face?

Jeans Pawl

I was stuck here, too. Yet, the solution is shown right in the error message: "To accept these channels' Terms of Service, run the following commands:" So you need to press WIN+R, type CMD, and press Enter to open the command line tool. In this console, copy and paste and confirm (press enter) all single entries that are listed in your error message. So in this case: 1) conda tos accept --override-channels --channel https://repo.anaconda.com/pkgs/main 2) conda tos accept --override-channels --channel https://repo.anaconda.com/pkgs/r 3) conda tos accept --override-channels --channel https://repo.anaconda.com/pkgs/msys2 Then delete the folder the installer already had created and run the .BAT-File again. (The installer will quit without further notice if you do not delete that folder with the failed installation, first.)

Aitrepreneur

I had that too, you can create a new conda env and then activate it sowhere in some folder. you can use these commands for example: conda create -n myenv conda activate myenv it should then give you the possibility to accept the tos, then you can relaunch the installer

Teresa Greasley

It's ok I see now you can use various different models and change them as needed.

theRCB

can i use the big model on my 4090?

theRCB

was the auto isntaller supposed to auto install the models?

Lance Fanger

When using one click installer I am getting this error: line 9, in import yaml ModuleNotFoundError: No module named 'yaml'

neil

when i click the bat it opens then closes straight away

Colliebii

The same thing happens to me. Did you find out how to fix it?

Piros07

install Git it work for me

Mad Monkey

I had the same problem and this helped me too

William

Got this error at the end: ******************************************************************* * You haven't downloaded any model yet. * Once the web UI launches, head over to the "Model" tab and download one. ******************************************************************* bash: -c: line 1: syntax error near unexpected token `)' bash: -c: line 1: `. "/workspace/text-generation-webui/installer_files/conda/etc/profile.d/conda.sh" && conda activate "/workspace/

Art.

My TEXT-GEN_WEBUI_INSTALLER closes automatically when I try to install it.. I Got GitHub. I need help

James Hanggi

Greetings K, when will you be adding the follow-on video for this post? I am fascinated by the possibilities of this generator!