# liltom-eth/llama2-webui

Run any Llama 2 locally with gradio UI on GPU or CPU from anywhere (Linux/Windows/Mac). Use `llama2-wrapper` as your local llama2 backend for Generative Agents/Apps.

Repository: https://github.com/liltom-eth/llama2-webui
Canonical: https://ross.abutalabs.com/products/llama2-webui
Language: Jupyter Notebook
License: MIT
License Family: permissive
Topics: llama-2, llama2, llm, llm-inference
Last push: 2024-03-22T09:50:24+00:00

## Health v2 (maintenance only)
Score: 19/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 81
- inputs: {"age_days": 1141, "days_push": 894, "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 1937, forks 199 (observed 2026-08-28T04:05:57.145607+00:00)

## What it is
A Gradio-based web UI for running Llama 2 models (7B/13B/70B, GPTQ, GGML, GGUF, CodeLlama) locally on GPU or CPU across Linux, Windows, and Mac. It also ships llama2-wrapper, a Python backend for integrating Llama 2 into generative agent apps, plus an OpenAI-compatible API server.

## Use cases
- run llama 2 locally with a chat ui
- serve llama2 on cpu or mac without gpu
- use llama2 as backend for generative agents
- run an openai-compatible api on local llama2 models
- run quantized 4-bit or 8-bit llama2 models
- try code llama in a browser playground

## When to choose
- you want a simple local web UI for Llama 2 variants on any OS
- you need a Python wrapper to embed Llama 2 in your own apps
- you want OpenAI API compatibility with local models

## When to avoid
- you need multi-user production serving with high throughput
- you want broader model support beyond Llama 2 family
- you need an actively developed feature-rich UI like newer alternatives

## Facets
- artifact type: application
- maturity: maintenance
- function: llm-inference, chat-interface, web-framework, sdk
- domain: large-language-models, artificial-intelligence, self-hosted, developer-tools
- platform: windows, python, cross-platform, cli
- tags: llama-2, gradio, llama-cpp, gptq, gguf, openai-compatible-api, local-inference, chatbot-ui, linux, macos, gpu

## Member repositories
- liltom-eth/llama2-webui (main) score 19

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:57.145607+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 2026-08-30T03:08:14.473390+00:00, confidence not recorded.
  - readme: https://github.com/liltom-eth/llama2-webui (fetched 2026-08-28T04:05:57.145607+00:00, sha c1789d9e5eb1)
- Data as of 2026-08-30T08:39:29.467469+00:00.