Alternatives to TextGen
Chat with local language models using the TextGen desktop interface. The listings below can replace it for an important use case. Each note says what changes if you switch.
The original
TextGen
Chat with local language models using the TextGen desktop interface.
Replacements
Listings that take over the same core job as TextGen.
LM Studio
A polished desktop app for downloading, running and chatting with local language models, with an OpenAI-compatible server built in.
LM Studio is a closed-source desktop app that searches and downloads Hugging Face models in-app and serves them on OpenAI-compatible endpoints, with MLX support for Apple Silicon.
KoboldCpp
A single executable that runs GGUF language models locally, with a web interface and no installation at all.
KoboldCpp is a single AGPL-3.0 executable for GGUF models with no installation, handling text, images and speech, though its bundled interface is dense.
Jan
An open-source ChatGPT replacement that runs entirely offline, and can also front cloud providers when you want them.
Jan is an Apache 2.0 desktop app that runs models offline and can also front cloud providers from the same interface, though it is still pre-1.0.
GPT4All
A local AI chat app with document chat built in, from Nomic AI. Stable, MIT licensed, but not updated since early 2025.
GPT4All is an MIT desktop app that runs on CPU without a GPU and answers from local documents, but its latest release dates from February 2025.
Ollama
The simplest way to pull down an open language model and run it on your own machine, from one command or a desktop app.
Ollama is an MIT tool that downloads and runs a model with one command and exposes a localhost REST API, with a desktop app rather than a full chat interface.
Msty
Desktop workspace for chatting with local and hosted AI models in one place.
Msty is a closed-source desktop workspace for local and hosted models with prompt libraries and knowledge bases, and more capable features sit behind a paid plan.
Open WebUI
A self-hosted chat interface that talks to Ollama and any OpenAI-compatible API, so your local models get a proper front end.
Open WebUI is a self-hosted multi-user web interface with document retrieval that fronts Ollama and OpenAI-compatible APIs instead of running models itself.
llama.cpp
The C++ engine most local AI apps are built on, running language models on ordinary hardware.
llama.cpp is the MIT C++ engine with a built-in server and basic web interface, command line first, with many GPU backends and aggressive quantisation.
Also worth comparing
These listings name TextGen as their own alternative, so the relationship runs both ways.
SillyTavern
A locally-installed front end for language models aimed at long-form roleplay and character-driven writing.
TextGen is an AGPL-3.0 desktop interface that runs local models itself with portable builds and API access, but lacks the character cards and lorebooks SillyTavern offers.
Similar software
Related functionality, not a direct replacement.
Chatbox
A desktop and mobile chat client for AI models, where you supply your own API keys or point it at a local model.
llamafile
Packages a language model and the code to run it into one executable file that works on several operating systems without installation.
LocalAI
Serve language, image and speech models on your own hardware.
vLLM
High-throughput, memory-efficient inference and serving engine for LLMs.
AnythingLLM
A desktop AI app that answers questions about your own documents, with no account and no API key needed.
