Resources

Everything you need to get started

Realistic sample datasets to put Datally through its paces, plus a complete guide to running the AI locally.

Demo datasets

Sample datasets

Each pack includes multiple source files, a reference dictionary, and intentional data-quality issues — exactly the mess Datally is built for.

Residential Loan Tape

Finance

Multi-servicer mortgage data from 5 different origination and servicing platforms.

100 loans across 5 servicer platforms

Every target field mappable from a source

Realistic naming variations across sources

Different date, rate, and LTV formats

Reference dictionary with 30 standardized fields

Value translation examples (codes, enums)

Credit Union · Rocket Mortgage · Wells Fargo · Mr. Cooper · Legacy System

DownloadZIP · 72 KB · 5 source CSVs + dictionary

Insurance Claims Bordereau

Insurance

Multi-source claims data from email submissions, adjuster tracking, and inspection vendors.

15 claims across 3 source systems

Different status codes (Open vs Active vs OPEN)

Inconsistent date and currency formatting

Loss-type abbreviations vs full text

Email Submissions · Adjuster Tracking · Inspection Vendor Data

DownloadZIP · 4 KB · 3 source CSVs + dictionary

E-Commerce Orders

Retail

Multi-channel order data from Shopify, Amazon, and WooCommerce.

35 orders across 3 sales channels

Different column naming patterns

Reference dictionary schema

15+ intentional data quality issues

Order-status & payment-method translation

Shopify · Amazon · WooCommerce

DownloadZIP · 10.8 KB · 4 CSVs + README

HR Payroll

HR / Payroll

Multi-source employee and payroll data from four different HR systems.

ADP Workforce employee records

BambooHR employee data

Paychex payroll roster

Workday export dictionary

ADP · BambooHR · Paychex · Workday

DownloadZIP · 7.3 KB · 4 CSVs + README

Local AI

Run the AI on your own machine

Optional setup for local AI assistance. Automatic uses compatible models available on your machine; you can start with deterministic matching and review before installing any models.

Choose models that fit your hardware

GPU (8GB+ VRAM): recommended for the tested local LLM and embedding pair.

4–6GB or CPU-only: use the labeled lower-memory models; deterministic workflows remain available.

Install Ollama (Windows)

Ollama is free and open source. Recommended via Windows Package Manager:

winget install --id=Ollama.Ollama -eOr download manually for Windows

After installing, Ollama runs as a background service on port 11434.

Download recommended models

Language models · GPU

granite4.2:8bRecommended

IBM Granite 4.2 — Datally's tested default for accurate mapping on 8GB+ GPUs.

ollama pull granite4.2:8b

gemma4:12bQuality alternate

Google Gemma 4 — accurate structured output with a larger memory footprint.

ollama pull gemma4:12b

qwen3.5:4bLower memory

Qwen 3.5 4B — a compact option for 4–6GB GPUs when speed matters more than peak mapping quality.

ollama pull qwen3.5:4b

Embedding models

qwen3-embedding:8bRecommended

Datally's tested default and the strongest Fast-mode mapping result among the local candidates.

ollama pull qwen3-embedding:8b

qwen3-embedding:4bLower memory

Matched the 8B model in Accurate mode, but produced fewer correct Fast-mode mappings.

ollama pull qwen3-embedding:4b

nomic-embed-text-v2-moeMultilingual alternate

A compact multilingual retrieval option when the recommended Qwen model is too large.

ollama pull nomic-embed-text-v2-moe

CPU-only / integrated GPU

granite-embedding:30mFastest

IBM Granite — optimized for CPU inference.

ollama pull granite-embedding:30m

granite-embedding:278mBetter quality

IBM Granite 278M — higher quality with 12+ language support.

ollama pull granite-embedding:278m

Verify installation

List installed models:ollama list

Test a model:ollama run granite4.2:8b "Hello"

Launch Datally and start Automatic preparation. Use Settings if you want to choose models explicitly.

Support

Documentation & support

Getting-started guide

Step-by-step tutorials and best practices for your first consolidation.

Read the guide

Technical support

Stuck on something? We’re glad to help.

Contact support

Ready to try the desktop app?

Request Datally trial access, then run your first reconciliation with one of the sample datasets above.