# alexrozanski/LlamaChat

Chat with your favourite LLaMA models in a native macOS app

Repository: https://github.com/alexrozanski/LlamaChat
Canonical: https://ross.abutalabs.com/products/llamachat
Homepage: https://llamachat.app
Language: Swift
License: MIT
License Family: permissive
Topics: ai, llama, llamacpp, machine-learning, macos, swift, swiftui
Last push: 2026-06-17T02:03:57+00:00

## Health v2 (maintenance only)
Score: 60/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 87, release rhythm 8, longevity 89
- inputs: {"age_days": 1257, "days_push": 78, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1511, forks 60 (observed 2026-08-28T04:04:55.964644+00:00)

## What it is
LlamaChat is a native macOS app for chatting with LLaMA, Alpaca, GPT4All and similar models running entirely locally on your Mac. It is built on llama.cpp and llama.swift, supports importing raw PyTorch checkpoints or .ggml files, and persists chat history.

## Use cases
- chat with llama models locally on mac
- run alpaca model in a native macos app
- convert pytorch checkpoints to ggml
- offline chatbot without cloud services
- chat with gpt4all models on apple silicon
- inspect model context while chatting

## When to choose
- you want a polished native macOS UI for local LLaMA-family models
- you need fully offline inference with no data leaving your machine
- you want built-in conversion of raw PyTorch checkpoints to .ggml

## When to avoid
- you need GPU-cluster or multi-user server deployments
- you want the latest model formats like GGUF or newer model families
- you need a cross-platform or Windows/Linux client

## Facets
- artifact type: application
- maturity: maintenance
- function: llm-inference, chatbot, chat-interface
- domain: large-language-models, artificial-intelligence, apple-ecosystem, desktop-applications
- platform: -
- tags: llama, llamacpp, swiftui, local-llm, ggml, alpaca, gpt4all, native-macos-app, macos, swift, desktop

## Member repositories
- alexrozanski/LlamaChat (main) score 60

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:55.964644+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:32:22.763986+00:00, confidence not recorded.
  - readme: https://github.com/alexrozanski/LlamaChat (fetched 2026-08-28T04:04:55.964644+00:00, sha 0102c74555f0)
  - homepage: https://llamachat.app (fetched 2026-08-29T11:36:16.581085+00:00, sha b6a415101f90)
- Data as of 2026-08-30T08:39:29.467469+00:00.