Alternatives to RWKV Runner
A small desktop app that downloads and runs RWKV language models locally with an OpenAI-compatible API. The listings below can replace it for an important use case. Each note says what changes if you switch.
The original
RWKV Runner
A small desktop app that downloads and runs RWKV language models locally with an OpenAI-compatible API.
Replacements
Listings that take over the same core job as RWKV Runner.
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 runs many open model families from one command with a localhost REST API, instead of being limited to RWKV models, and is MIT licensed.
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 polished closed-source desktop app that downloads many Hugging Face models and serves OpenAI-compatible endpoints, not only RWKV models.
KoboldCpp
A single executable that runs GGUF language models locally, with a web interface and no installation at all.
KoboldCpp is a single executable for GGUF models with OpenAI and Ollama compatible endpoints, plus image, speech and vision support, under AGPL-3.0.
llama.cpp
The C++ engine most local AI apps are built on, running language models on ordinary hardware.
llama.cpp runs a wide range of quantised models with a built-in server and many GPU backends, but is command-line first rather than a desktop app.
Jan
An open-source ChatGPT replacement that runs entirely offline, and can also front cloud providers when you want them.
Jan is an Apache licensed desktop chat app for local models that can also front cloud providers, rather than an RWKV-focused runner.
LocalAI
Serve language, image and speech models on your own hardware.
LocalAI serves language, image and speech models behind compatible APIs on Linux and macOS, and suits self-hosted setups more than a small desktop app.
TextGen
Chat with local language models using the TextGen desktop interface.
TextGen is an AGPL desktop interface for many local model types with text, vision and API access, and ships portable builds.
llamafile
Packages a language model and the code to run it into one executable file that works on several operating systems without installation.
llamafile packs a model and runtime into one executable for several operating systems, but lacks RWKV Runner's fine-tuning tools.
Similar software
Related functionality, not a direct replacement.
TabbyAPI
A lightweight, OpenAI-compatible API server for running ExLlama-format language models on your own hardware.
llama-swap
A proxy server that loads and hot-swaps local AI model servers on demand behind one API.
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.
Chatbox
A desktop and mobile chat client for AI models, where you supply your own API keys or point it at a local model.
Unsloth
A local interface and command-line tool for running and fine-tuning language and diffusion models.
