# jncraton/languagemodels

Explore large language models in 512MB of RAM

Repository: https://github.com/jncraton/languagemodels
Canonical: https://ross.abutalabs.com/products/languagemodels
Homepage: https://jncraton.github.io/languagemodels/
Language: HTML
License: MIT
License Family: permissive
Topics: llm, nlp, python
Last push: 2026-02-19T16:34:49+00:00

## Health v2 (maintenance only)
Score: 60/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 68, release rhythm 35, longevity 86
- inputs: {"age_days": 1215, "days_push": 195, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1192, forks 80 (observed 2026-08-28T04:03:56.322370+00:00)

## What it is
A Python library providing simple building blocks for running large language models locally with as little as 512MB of RAM. It offers instruction following, text completion, retrieval, and other NLP tasks with all inference performed on-device for privacy.

## Use cases
- run an llm locally in python with minimal ram
- ask questions to a local language model from a script
- translate text offline with a small model
- classify text into fixed choices using an llm
- complete text with a local model
- retrieve passages for rag without external services
- keep llm inference private on-device

## When to choose
- you need local, private LLM inference on constrained hardware like 512MB RAM
- you want a dead-simple Python API for small language models
- you're teaching or prototyping LLM concepts without GPUs or cloud APIs

## When to avoid
- you need state-of-the-art model quality or long-context reasoning
- you require high-throughput production serving
- you need fine-tuning or training capabilities

## Facets
- artifact type: library
- maturity: active
- function: llm-inference, nlp, rag, sdk
- domain: large-language-models, machine-learning
- platform: python, cross-platform
- tags: local-inference, low-resource, on-device-llm, privacy, small-models, natural-language-processing

## Member repositories
- jncraton/languagemodels (main) score 60

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:56.322370+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 2026-08-30T06:22:30.289590+00:00, confidence not recorded.
  - readme: https://github.com/jncraton/languagemodels (fetched 2026-08-28T04:03:56.322370+00:00, sha ecdf0d8c88c3)
  - homepage: https://jncraton.github.io/languagemodels/ (fetched 2026-08-29T12:29:34.713480+00:00, sha 44136fa355b3)
- Data as of 2026-08-30T08:39:29.467469+00:00.