# Ollama

> Run open models on your own computer.

Ollama has a SharkScore of 83.9/100, ranked #1 of 6 in Model APIs & inference (updated 2026-11-17).

- Website: https://ollama.com (ollama.com)
- Kind: Tool · Pricing: Open source
- Repository: https://github.com/ollama/ollama
- Categories: Model APIs & inference, Models
- Verified by the maker: no

## Why it scores 83.9

| Part | Score (0–100) | Weight |
|---|---|---|
| Adoption | 97 | 30% |
| User reviews | 95 | 25% |
| Maintenance | 100 | 20% |
| Trust & transparency | 60 | 15% |
| Momentum | 20 | 10% |

Evidence covers 100% of the score's weight. Compared with other listings in Model APIs & inference.

## Evidence

| Signal | Value |
|---|---|
| Monthly visits | — |
| GitHub stars | 158K |
| Stars, last 90 days | +7K |
| Downloads, 30 days | — |
| Reviews | 4.8 stars from 92 |
| Last update | 2 days ago |
| Uptime, 30 days | — |
| Public pricing / Free tier / API / MCP | yes / yes / no / no |

## Top alternatives

1. [Hugging Face](https://rankshark.pro/tools/hugging-face) — SharkScore 83.1. The home of open models, datasets and Spaces.
2. [OpenRouter](https://rankshark.pro/tools/openrouter) — SharkScore 75.2. One API for hundreds of models, with fallbacks.
3. [Groq](https://rankshark.pro/tools/groq) — SharkScore 73.9. Very fast inference for open models.
4. [Replicate](https://rankshark.pro/tools/replicate) — SharkScore 72.0. Run open models with one line of code.
5. [Together AI](https://rankshark.pro/tools/together-ai) — SharkScore 70.2. Run, fine-tune and train open models in the cloud.

---
Source: https://rankshark.pro/tools/ollama · Method v2026-11-17.1: https://rankshark.pro/how-ranking-works · Payment never changes a rank.
