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.

---

⚡ 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

{
  "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

---

⚖️ License & Attribution

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