# Ollama Models Intelligence & Local AI LLM Matrix (`primesieve/ollama-models-intel`) Actor

Discover, monitor, and compare Ollama models, quantization tags, parameter sizes (VRAM requirements), pull counts, and capabilities (tools, vision, embedding). Zero proxy needed.

- **URL**: https://apify.com/primesieve/ollama-models-intel.md
- **Developed by:** [Prime Sieve](https://apify.com/primesieve) (community)
- **Categories:** AI, Developer examples
- **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

Pay per usage

This Actor is paid per platform usage. The Actor is free to use, and you only pay for the Apify platform usage, which gets cheaper the higher subscription plan you have.

Learn more: https://docs.apify.com/actors/running/actors-in-store.md#pay-per-usage

## What's an Apify Actor?

An Actor is a serverless cloud program that runs on the Apify platform. It has two run modes.
In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours,
and optionally produces a well-defined JSON output, datasets with results, or files in key-value store.
In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server.

Apify vocabulary and the platform model are defined once, in the agent quickstart at https://apify.com/agents.md.

## How to integrate an Actor?

If asked about integration, you help developers integrate Actors into their projects.
You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready.

Do not guess an integration path. Every one of them is in the agent quickstart at https://apify.com/agents.md: the Apify MCP server, Agent Skills with the Apify CLI, the JavaScript and Python clients, the REST API, and the account-free path for an agent with no human to sign in. It also carries the rule on stating cost before the first paid run.

For examples already wired to this Actor's own input schema, see the [API](#api) section below.

Each client library has reference documentation the quickstart does not restate: [JavaScript/TypeScript](https://docs.apify.com/api/client/js/docs.md) (`npm install apify-client`) and [Python](https://docs.apify.com/api/client/python/docs.md) (`pip install apify-client`).

# README

## Ollama Models & Local AI Ecosystem Intelligence Scraper 🦙

> Comprehensive real-time market intelligence, quantization sizes, VRAM capacity planning, and pull analytics for every model hosted on the official Ollama library.

[![Prime Sieve](https://img.shields.io/badge/Prime_Sieve-Ecosystem_Intel-0ea5e9?style=flat-square)](https://remotesignal.substack.com)
[![Zero Proxy](https://img.shields.io/badge/Proxy-Zero_Proxy_Fast-success?style=flat-square)](#)
[![Output Format](https://img.shields.io/badge/Output-JSON%20%7C%20CSV%20%7C%20Excel-blue?style=flat-square)](#)

***

### ⚡ Why Use Ollama Models Intel?

Local AI inference and self-hosted open-source models are growing exponentially. Whether you are sizing server infrastructure, provisioning edge hardware, building multi-agent local stacks, or monitoring open weights adoption, you need precise and up-to-date data on models, quantization tags, parameter sizes, and download footprints.

This actor scrapes and extracts the full intelligence matrix from Ollama:

- **Ecosystem Adoption & Ranking**: Live pull counts (e.g. `119.6M` pulls), update dates, and tag counts.
- **Hardware & VRAM Capacity Matrix**: Quantization tags (`q4_K_M`, `q8_0`, `fp16`, etc.) with exact disk and memory footprints (`4.9GB`, `43GB`, `243GB`).
- **Context Windows**: Context window limits (`128K`, `32K`, `8K`).
- **Capability Flags**: Identifies function calling (`tools`), multimodal (`vision`), embeddings (`embedding`), and reasoning (`thinking`) models.
- **Zero Proxy Overhead**: Runs lightweight, direct HTTP with zero proxy charges.

***

### 🚀 Key Features

- **Full Catalog Discovery**: Extracts models from `ollama.com/library`.
- **Deep Tag & Quantization Breakdown**: Inspects all available parameter sizes and quantization levels per model.
- **Capability Filtering**: Filter directly for `tools`, `vision`, `embedding`, or `thinking` architectures.
- **Market Summary Insights**: Aggregates total ecosystem pulls and capability distribution into a single overview record.

***

### 📥 Input Parameters

| Field | Type | Default | Description |
|---|---|---|---|
| `searchQuery` | String | `""` | Filter models by keyword (e.g. `deepseek`, `llama`, `qwen`, `vision`) |
| `category` | Select | `"all"` | Filter by capability: `all`, `tools`, `vision`, `embedding`, `thinking` |
| `maxModels` | Integer | `100` | Maximum number of models to extract (1–300) |
| `fetchTagDetails` | Boolean | `true` | Fetch individual quantization sizes and context limits |
| `includeSummary` | Boolean | `true` | Generate an ecosystem summary and analytics record |

***

### 📊 Sample Output Data

```json
{
  "name": "deepseek-r1",
  "description": "DeepSeek-R1 is a family of open reasoning models with performance approaching that of leading models, such as O3 and Gemini 2.5 Pro.",
  "pullCount": "92.9M",
  "pullCountNumeric": 92900000,
  "totalTags": 35,
  "parameterSizes": [
    "1.5b",
    "7b",
    "8b",
    "14b",
    "32b",
    "70b",
    "671b"
  ],
  "capabilities": [
    "tools",
    "thinking"
  ],
  "defaultSize": "4.7GB",
  "contextWindow": "128K context",
  "tagsList": [
    {
      "tag": "deepseek-r1:latest",
      "size": "4.7GB"
    },
    {
      "tag": "deepseek-r1:7b",
      "size": "4.7GB"
    },
    {
      "tag": "deepseek-r1:8b",
      "size": "4.9GB"
    },
    {
      "tag": "deepseek-r1:14b",
      "size": "9.0GB"
    },
    {
      "tag": "deepseek-r1:32b",
      "size": "20GB"
    },
    {
      "tag": "deepseek-r1:70b",
      "size": "43GB"
    },
    {
      "tag": "deepseek-r1:671b",
      "size": "404GB"
    }
  ],
  "lastUpdated": "Jul 2, 2025 6:09 AM UTC",
  "url": "https://ollama.com/library/deepseek-r1",
  "scrapedAt": "2026-09-18T10:00:00.000Z"
}
```

***

### 📬 Stay Connected — Remote Signal Newsletter

Want weekly curated intelligence on autonomous AI agent stacks, high-yield developer opportunities, and solo-dev engineering architectures?

👉 **[Subscribe to Remote Signal Newsletter](https://remotesignal.substack.com)**

***

### ⚖️ License & Attribution

Maintained by **Prime Sieve**. Built for developers, AI engineers, and DevOps teams running local AI infrastructure.

# Actor input Schema

## `searchQuery` (type: `string`):

Filter models by name, architecture, or capability (e.g. 'deepseek', 'llama', 'vision', 'qwen'). Leave blank for all models.

## `category` (type: `string`):

Filter by specific model capability category

## `maxModels` (type: `integer`):

Maximum number of models to scrape and analyze (1 - 300).

## `fetchTagDetails` (type: `boolean`):

Fetch individual quantization variants (Q4\_K\_M, Q8\_0, FP16), exact file sizes, and context windows for each model.

## `includeSummary` (type: `boolean`):

Push an analytics overview item summarizing total ecosystem pulls, category distribution, and top trending models.

## Actor input object example

```json
{
  "searchQuery": "",
  "category": "all",
  "maxModels": 100,
  "fetchTagDetails": true,
  "includeSummary": true
}
```

# Actor output Schema

## `name` (type: `string`):

Unique model identifier on Ollama library (e.g. deepseek-r1, llama3.1)

## `description` (type: `string`):

Overview and architecture summary of the model

## `pullCount` (type: `string`):

Human-readable pull count string (e.g. 119.6M, 850K)

## `pullCountNumeric` (type: `string`):

Exact numeric estimated pull count for sorting and market share analysis

## `totalTags` (type: `string`):

Total number of quantization and parameter tags

## `parameterSizes` (type: `string`):

List of available parameter sizes (e.g. 1.5b, 7b, 8b, 70b)

## `capabilities` (type: `string`):

Supported capabilities (tools, vision, embedding, thinking)

## `defaultSize` (type: `string`):

File size for the default/latest quantization tag

## `contextWindow` (type: `string`):

Context window limit (e.g. 128K, 32K, 8K)

## `lastUpdated` (type: `string`):

Timestamp when the model was updated on Ollama

## `url` (type: `string`):

Direct link to Ollama library page

# API

You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup.

## JavaScript example

```javascript
import { ApifyClient } from 'apify-client';

// Initialize the ApifyClient with your Apify API token
// Replace the '<YOUR_API_TOKEN>' with your token
const client = new ApifyClient({
    token: '<YOUR_API_TOKEN>',
});

// Prepare Actor input
const input = {};

// Run the Actor and wait for it to finish
const run = await client.actor("primesieve/ollama-models-intel").call(input);

// Fetch and print Actor results from the run's dataset (if any)
console.log('Results from dataset');
console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
items.forEach((item) => {
    console.dir(item);
});

// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs

```

## Python example

```python
from apify_client import ApifyClient

# Initialize the ApifyClient with your Apify API token
# Replace '<YOUR_API_TOKEN>' with your token.
client = ApifyClient("<YOUR_API_TOKEN>")

# Prepare the Actor input
run_input = {}

# Run the Actor and wait for it to finish
run = client.actor("primesieve/ollama-models-intel").call(run_input=run_input)

# Fetch and print Actor results from the run's dataset (if there are any)
print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")
for item in client.dataset(run.default_dataset_id).iterate_items():
    print(item)

# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start

```

## CLI example

```bash
echo '{}' |
apify call primesieve/ollama-models-intel --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,primesieve/ollama-models-intel"
        }
    }
}
```

The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer <APIFY_API_TOKEN>` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations).

## OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/actors/4UlLiejNhLVKzPlDd/builds/rcAp8KpxIqPL0feBC/openapi.json