Blogs

Discover the latest insights, guides, and updates on AI orchestration, real-time systems, and modern event-driven communication with DNotifier.

Keeping Your Local Models Fresh
Insights

Keeping Your Local Models Fresh

Part seven of the DNotifier × Ollama series — no vendor retirement schedule, manual ollama pull cycles, and quarterly freshness checks.

DNotifier Team
9 min read
#ollama#model-updates#operations
Tool Calling on Local Models
Insights

Tool Calling on Local Models

Tool calling and structured output on Ollama work, but reliability depends on the model. How to test local models before trusting them in production workflows.

DNotifier Team
10 min read
#ollama#tool-calling#structured-output
When Local Beats Cloud (And When It Doesn't)
Insights

When Local Beats Cloud (And When It Doesn't)

Part five of the DNotifier × Ollama series — air-gapped and data-boundary cases, cloud capability ceiling, and mixed local/cloud workflows per step.

DNotifier Team
10 min read
#ollama#local-models#cloud
Ollama Hardware: VRAM & Quantization
Insights

Ollama Hardware: VRAM & Quantization

How much VRAM Ollama models need, what quantization trades away in quality, when CPU-only inference works, and when self-hosting stops being worth it.

DNotifier Team
10 min read
#ollama#vram#gpu
Choosing a Model to Run Locally
Insights

Choosing a Model to Run Locally

Part three of the DNotifier × Ollama series — parameter count, GGUF quantization, task-first selection, and Prompt Testing Studio on local models.

DNotifier Team
10 min read
#ollama#quantization#model-selection
What Makes Ollama Different?
Insights

What Makes Ollama Different?

Ollama runs LLMs on your own hardware: no per-token bill, no rate limits, data stays local. What you gain and what you give up versus cloud providers.

DNotifier Team
9 min read
#ollama#local-models#privacy
Ollama on DNotifier: Setup Guide
Insights

Ollama on DNotifier: Setup Guide

Part one of the DNotifier × Ollama series — configure a reachable base URL, pull models with ollama, and call local inference through provider ollama and sendAI().

DNotifier Team
10 min read
#ollama#local-models#self-hosted
Avoiding Lock-In: Azure and Beyond
Insights

Avoiding Lock-In: Azure and Beyond

Part ten of the DNotifier × Azure AI series — Foundry complexity, API retirements, deployment blast radius, and the seven-provider orchestration throughline.

DNotifier Team
11 min read
#azure-ai#multi-provider#lock-in
Entra ID vs. API Keys on Azure
Insights

Entra ID vs. API Keys on Azure

When to use API keys vs Microsoft Entra ID for Azure OpenAI: RBAC, managed identities, key rotation, and choosing auth by team size.

DNotifier Team
9 min read
#azure-ai#entra-id#api-keys