TextGen
Desktop app for running local LLMs with vision, tool-calling, and APIs.
Run private models with multiple backends, vision, and tool-calling support.
Textgen is an open-source desktop application that lets you run and interact with large language models locally on your own hardware. It is ideal for professionals seeking a fully private, offline interface for text generation, translation, and model experimentation.
What it is
The application provides a unified interface and OpenAI/Anthropic-compatible API for various model backends including llama.cpp and Transformers. It supports multi-turn chat, vision tasks with image attachments, document parsing, custom tool-calling via Python files, and LoRA fine-tuning.
Who it's for
It suits developers, translators, and writers who need strict data privacy and want to test or run local GGUF and safetensors models. It does not suit users looking for a zero-setup cloud service or those without compatible GPU hardware.
Key features
Multiple Backends
Switch between llama.cpp, Transformers, ExLlamaV3, and TensorRT-LLM without restarting.
Vision and Documents
Attach images, PDFs, and Word documents to chat messages for multimodal analysis.
OpenAI-Compatible API
Use local endpoints with Chat, Completions, and tool-calling support as a drop-in replacement.
Built-in Training
Fine-tune LoRAs on multi-turn chat or raw text datasets directly within the application.
Up and running in 3 steps
Our honest verdict
What's great
- Supports multiple model backends including GGUF and Transformers
- Provides an OpenAI and Anthropic-compatible API with tool-calling
- Includes multimodal vision support and file attachments for PDFs and docs
- Offers dedicated tabs for LoRA training and image generation
Where it falls short
- Requires significant local hardware resources and disk space for full installations
- Manual setup is needed for non-portable backends like Transformers and ExLlamaV3
- No built-in cloud sync or managed hosting options are provided
Pricing & license
The software is free under its open-source license. The only cost is running it on your own hardware or renting compatible GPU instances.
Open remote AI-training roles
870 open remote AI-training roles, updated November 14, 2026; most pay $20–$170 an hour. Zekai lists them free; the application goes to the employer’s platform.
Alternatives
These reviewed AI tools do the same job instantly — from our scored directory.
