# GoogleCloudPlatform/localllm

Repository: https://github.com/GoogleCloudPlatform/localllm
Canonical: https://ross.abutalabs.com/products/localllm
Language: Python
License: Apache-2.0
License Family: permissive
Archived: true
Last push: 2024-04-25T02:55:00+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 72
- inputs: {"age_days": 1009, "days_push": 860, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1550, forks 119 (observed 2026-08-28T04:05:02.140273+00:00)

## What it is
A CLI tool and Docker image for running quantized LLMs locally on Google Cloud Workstations using llama-cpp-python's web server. It packages Hugging Face quantized models behind an OpenAI-compatible local endpoint.

## Use cases
- run llms locally on cloud workstations
- serve quantized huggingface models with llama.cpp
- self-host an openai-compatible llm endpoint
- use local llms for code assistance without sending data externally
- spin up a workstation image with an llm tool preinstalled

## When to choose
- you use Google Cloud Workstations and want local LLM inference
- you want quantized models served via llama-cpp-python without GPU setup
- you need a private, on-cloud LLM endpoint for developer tooling

## When to avoid
- you need high-throughput production inference with GPU acceleration
- you are not on GCP and just want a simple local LLM runner
- you need the latest model architectures beyond llama.cpp support

## Facets
- artifact type: cli-tool
- maturity: maintenance
- function: llm-inference, cli, http-server
- domain: large-language-models, developer-tools, cloud-computing
- platform: python, cloud, cli
- tags: llama-cpp, quantized-models, huggingface, google-cloud, cloud-workstations, local-inference, docker

## Member repositories
- GoogleCloudPlatform/localllm (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:02.140273+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 2026-08-30T04:30:18.968496+00:00, confidence not recorded.
  - readme: https://github.com/GoogleCloudPlatform/localllm (fetched 2026-08-28T04:05:02.140273+00:00, sha 2728fef71118)
- Data as of 2026-08-30T08:39:29.467469+00:00.