LIVE
Google Introduces "Gemini 4 Carbon" as Next Step in Its Model Lineup28/10/26 · Google|DeepMind unveils Genie 4, a new generation of world model27/10/26 · Google DeepMind|Anthropic files IPO prospectus, with risk disclosures taking center stage26/10/26 · Anthropic|Robot policy trained only in simulation matches top real-world systems26/10/26|OpenAI unveils GPT-6.1 Terra, a model built for computer use26/10/26 · OpenAI|Google's AI gives evasive answers about who won the 2020 US election28/10/26 · Google|NVIDIA introduces Nemotron 3.5 Transcribe, a promptable multilingual transcription model28/10/26 · NVIDIA|OpenAI and ServiceNow deepen partnership on enterprise workflows28/10/26 · OpenAI|Failed startups' data finds a second life training AI models28/10/26|Anthropic expands AI for Science program to 20 foundations and research institutions28/10/26 · Anthropic|Anthropic shares early results on using Claude to accelerate drug development27/10/26 · Anthropic|GEPA-Curator: Filtering Failures to Better Train LLM Agents27/10/26|Google Introduces "Gemini 4 Carbon" as Next Step in Its Model Lineup28/10/26 · Google|DeepMind unveils Genie 4, a new generation of world model27/10/26 · Google DeepMind|Anthropic files IPO prospectus, with risk disclosures taking center stage26/10/26 · Anthropic|Robot policy trained only in simulation matches top real-world systems26/10/26|OpenAI unveils GPT-6.1 Terra, a model built for computer use26/10/26 · OpenAI|Google's AI gives evasive answers about who won the 2020 US election28/10/26 · Google|NVIDIA introduces Nemotron 3.5 Transcribe, a promptable multilingual transcription model28/10/26 · NVIDIA|OpenAI and ServiceNow deepen partnership on enterprise workflows28/10/26 · OpenAI|Failed startups' data finds a second life training AI models28/10/26|Anthropic expands AI for Science program to 20 foundations and research institutions28/10/26 · Anthropic|Anthropic shares early results on using Claude to accelerate drug development27/10/26 · Anthropic|GEPA-Curator: Filtering Failures to Better Train LLM Agents27/10/26|
AppRisingofficial publisher

text-generation-webui

App : A product you use directly

Historic web interface for local LLMs, highly configurable.

Powerful for tinkerers, too complex for a beginner in 2026.

GitHub · 47,724 ★
Overall score
6.7 /10
Security: one caveat, see the card
Utility
6.0
Reliability
10.0
Security
One caveat
Ease
Technical · Technical

Security reflects where data goes, requested permissions and incidents on record at the verification date. It is not a guarantee of zero risk: check the deployment mode and the connections you enable.

What it does, concretely

text-generation-webui (also distributed as TextGen) addresses the need to run language models locally, without sending any data to a remote server. Everything stays on the user's machine, with zero telemetry or external resources.

In practice, the tool provides a graphical interface accessible from a browser or a desktop window. Users download a GGUF model file from Hugging Face, place it in the designated folder, and the interface detects it automatically. Several inference backends are available: llama.cpp, ExLlamaV3, Transformers, or TensorRT-LLM, and can be switched without restarting.

The tool is aimed at users comfortable with software installation, the command line, and fine-tuning parameters. It also suits developers who want a local API compatible with OpenAI and Anthropic formats to integrate a model into their own applications.

It is not suited for someone looking for a simple, immediate experience: the full installation requires around 10 GB of disk space, downloading PyTorch, and manually selecting the correct dependency file for one's hardware.

What it offers

  • ·Multiple conversation modes: instruction mode (similar to ChatGPT), chat mode with custom characters, and a notebook tab for free-form generation.
  • ·Multimodal vision: ability to attach images or files (PDF, text, .docx) to a message and discuss their contents with the model.
  • ·Tool-calling and web search: models can call custom functions during conversation, including web search and page fetching.
  • ·Local API compatible with OpenAI and Anthropic: allows using the tool as a local drop-in replacement for remote APIs, with tool-calling support.
  • ·Multiple inference backends supported: llama.cpp, ik_llama.cpp, ExLlamaV3, Transformers, and TensorRT-LLM, switchable without restarting.
  • ·LoRA training: fine-tune models on multi-turn chat or raw text datasets, with support for resuming interrupted runs.
  • ·Built-in image generation: dedicated tab for diffusers models with 4-bit and 8-bit quantization and a persistent gallery.
  • ·Community extensions: text-to-speech, voice input, translation, and other installable modules.

In practice

Price
Free
Commercial use
Commercial use: yes
Available on
windows, linux, macos
Licence
AGPL-3.0

Security and data

Rating
Security: one caveat, see the card
Your data
Data stays local
Maintenance
Active
Last release
20 May 2026

Links and repository checked on 25 October 2026 · added on 1 January 2023

How to install text-generation-webui

1. Go to https://github.com/oobabooga/textgen/releases and download the portable build for your system (Windows, Linux, or macOS) and hardware (CUDA, Vulkan, ROCm, or CPU). 2. Unzip the archive into a folder of your choice. 3. Double-click the textgen file to launch the application; a window opens directly. 4. Download a GGUF model file from Hugging Face and place it in the user_data/models folder: the interface detects it automatically. 5. Security note: the tool does not require administrator access to run; avoid exposing it on a public network without enabling Gradio authentication (--gradio-auth option).
python server.py --portable --api --auto-launch

In the same category

Whole category Run locally →