# signerless/llm-checker

Advanced CLI tool that scans your hardware and tells you exactly which LLM or sLLM models you can run locally, with full Ollama integration.

Repository: https://github.com/signerless/llm-checker
Canonical: https://ross.abutalabs.com/products/llm-checker
Homepage: https://www.npmjs.com/package/llm-checker
Language: JavaScript
License: NOASSERTION
License Family: other
Last push: 2026-08-25T22:16:14+00:00

## Health v2 (maintenance only)
Score: 84/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 96, longevity 30
- inputs: {"age_days": 423, "days_push": 8, "days_rel": 29, "gap_med": 0.5, "n_releases_24m": 19}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2935, forks 197 (observed 2026-08-28T04:07:30.728125+00:00)

## What it is
A Node.js CLI tool that scans your hardware (GPU, VRAM, CPU, memory) and recommends which LLM or small language models you can run locally, scoring models across quality, speed, fit, and context. It integrates with Ollama and draws from a multi-source registry of 33k+ artifacts from Hugging Face, Ollama, and GPT4All.

## Use cases
- find which LLM models my GPU can run locally
- recommend an Ollama model for my VRAM
- check if my hardware can run a 70B model
- pick the best small language model for my laptop
- compare local LLM models by speed and quality for my machine
- estimate memory needed for a quantized model

## When to choose
- you want to run LLMs locally with Ollama and are unsure which models fit your hardware
- you need hardware-aware recommendations across many model variants and quantization levels
- you want a zero-native-dependency Node.js tool with multi-GPU detection

## When to avoid
- you only run models in the cloud or via APIs and never locally
- you need a GUI-based model manager rather than a CLI
- you need a permissively licensed tool (license is NPDL-1.0, not standard open source)

## Facets
- artifact type: cli-tool
- maturity: active
- function: cli, llm-inference, developer-tools, machine-learning
- domain: large-language-models, developer-tools, machine-learning
- platform: cli, cross-platform, windows
- tags: ollama, hardware-detection, model-recommendation, vram, quantization, local-ai, mcp, command-line, nodejs, macos, linux

## Member repositories
- signerless/llm-checker (main) score 84

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:30.728125+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 2026-08-30T07:33:11.017445+00:00, confidence not recorded.
  - readme: https://github.com/signerless/llm-checker (fetched 2026-08-28T04:07:30.728125+00:00, sha 3a5acee53b9b)
  - registry_npm: https://registry.npmjs.org/llm-checker (fetched 2026-08-29T09:48:41.473223+00:00, sha 6df41de66f76)
- Data as of 2026-08-30T08:39:29.467469+00:00.