# Ollama

Get up and running with Kimi-K2.6, GLM-5.2, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

Repository: https://github.com/ollama/ollama
Canonical: https://ross.abutalabs.com/products/ollama
Homepage: https://ollama.com
Language: Go
License: MIT
License Family: permissive
Topics: llama, llm, llms, go, golang, ollama, mistral, gemma, llama3, deepseek, gemma3, qwen, gpt-oss, glm, minimax
Last push: 2026-08-26T23:11:12+00:00

## Health v2 (maintenance only)
Score: 92/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 87, longevity 83
- inputs: {"age_days": 1164, "days_push": 7, "days_rel": 7, "gap_med": 3.0, "n_releases_24m": 155}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 179521, forks 17575 (observed 2026-08-28T04:12:24.478844+00:00)

## What it is
Ollama is an open-source tool for downloading, running, and managing large language models locally on macOS, Windows, and Linux, with a simple CLI and a REST API. It ships official client libraries for Python and JavaScript and integrates with coding agents and chat applications.

## Use cases
- run large language models locally on my machine
- self-host an OpenAI-style LLM API server
- serve open models like Llama, Qwen, Gemma, or DeepSeek behind a REST API
- use local models with coding agents like Claude Code or Copilot
- chat with open-source models from the terminal
- build apps that call a local LLM via Python or JavaScript

## When to choose
- you want to run open models locally without cloud dependencies
- you need a simple local inference server with a REST API
- you want one-command model downloads and management
- you prefer privacy and offline LLM usage

## When to avoid
- you need high-throughput, multi-GPU production inference at scale
- you require fine-grained serving features like continuous batching or tensor parallelism
- you only want a hosted cloud LLM API

## Facets
- artifact type: application
- maturity: active
- function: llm-inference, http-server, cli, chatbot, rag
- domain: large-language-models, artificial-intelligence, developer-tools, self-hosted
- platform: windows, cli, python, self-hosted
- tags: local-llm, model-runner, open-models, rest-api, gguf, inference-server, macos, linux, docker, nodejs

## Member repositories
- ollama/ollama (main) score 92
- ollama/ollama-python (sdk) score 86
- ollama/ollama-js (sdk) score 61

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:12:24.478844+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 2026-08-29T16:10:43.897556+00:00, confidence not recorded.
  - readme: https://github.com/ollama/ollama (fetched 2026-08-28T04:12:24.478844+00:00, sha 405590137cea)
- Data as of 2026-08-30T08:39:29.467469+00:00.