Back to directory

Gerbil

A cross-platform desktop app, powered by KoboldCpp, for running large language models and generating images locally on a person's own hardware, with no telemetry, accounts or external servers.

Gerbil

Gerbil runs LLMs through KoboldCpp, a fork of llama.cpp, on Windows, macOS and Linux including Wayland, working on CPU-only systems as well as with GPU acceleration through CUDA, ROCm, Vulkan or Metal. It can import pre-downloaded KoboldCpp binaries and run fully offline, and includes built-in presets for image-generation workflows using Flux, Chroma, Qwen Image and Z-Image.

An integrated Hugging Face search browses models, views model cards, and downloads GGUF files directly from the app. It can also launch SillyTavern, for advanced character interactions, and OpenWebUI, for a web-based chat interface, as companion integrations when their own prerequisites (Node.js or uv) are present.

Pre-built binaries are provided for Windows, macOS and Linux, and an AUR package is available for Arch Linux; on macOS, the app must be manually removed from quarantine since it is not notarized by Apple.

More in Inference

See all 770
  • OpenDecision

    deepanwadhwa.github.io

    An open-source Python package that answers typed questions about application state or documents using a local natural-language-inference model, returning structured choice, score, yes/no or evidence-relation values instead of free text.

  • Lifeboat

    iterate.ai

    A local inference server that puts an OpenAI- and Anthropic-compatible API in front of open-weight language models running on hardware you control, from a laptop to a GPU cluster.

  • Claude S40

    github.com

    An unofficial Claude chat client for 2007-era Nokia Series 40 phones, built as a Java ME app plus a small Go relay server, with web search, reading mode and saved chats.