August 3, 2026

Apertus v1.5 70B on a single RTX PRO 6000 Blackwell

Apertus v1.5 70B ships as approximately 145 GB (135 GiB) of BF16 weights that officially need two H200 datacenter GPUs. We show how to run it on a single NVIDIA RTX PRO 6000 Blackwell with 96 GB VRAM, with vision input, native tool calling, and a 192k context profile (229k measured maximum). Using three-tier mixed-precision quantization (NVFP4 + FP8) it decodes 55% faster than FP8 while using 32% less weight storage, with 99% of FP8 MMLU quality.

July 28, 2026

Which AI Server Is Right for My Business?

Four on-premise AI server configurations compared: tokens per second, concurrent users, and what KV cache and context windows mean for your daily operations.

March 11, 2026

Why On-Premise AI Is Almost Always Safer

Free models, exposed credentials, and anonymization that does not hold up: why local AI is the only truly consistent answer to the security question.

December 12, 2025

API Standards for Large Language Models (LLM) AI

Practical guide to LLM API standards: OpenAI-compatible Chat Completion API for on-premise models (GPT-OSS, Llama, Qwen, DeepSeek), LiteLLM as unified gateway, control parameters, multimodality, structured outputs, tool calling and MCP. Everything developers need to know for enterprise LLM integration.

December 10, 2025

The Mathematics of AI Reliability: SLA-Based Capacity Planning Using Engset's Formula

How proven telecommunications mathematics ensures your on-premise AI infrastructure meets performance guarantees. A technical white paper on SLA-based capacity planning using Engset's formula.

December 7, 2025

AI Costs by Office Role: Token Consumption Patterns Across Your Team

Calculate the real AI costs for your team. From Executive Assistants to Software Engineers—understand what drives token consumption by office role and why developers are your biggest budget item.

December 7, 2025

Transparently Calculate On-Premises AI Costs

Our interactive cost calculator helps you accurately determine hardware requirements and costs for running your own Large Language Models, including a comparison of AMD and NVIDIA solutions.

December 7, 2025

Dataset: LLM Token Usage in Everyday Office Tasks

Comprehensive dataset of token consumption across 64 real-world AI tasks, including standard and reasoning models, with multimodal inputs.

September 19, 2025

On-Premise AI Solutions for every SME

On-premise AI for SMEs: Practical guide to models, hardware, and operations. Concrete recommendations on servers, data protection, and stability.