Skip to content
Bestin-it.com – IT services and analytics for entrepreneurs Blog about IT services and cutting-edge marketing technologies. Learn analytics that gives you insights and data-driven marketing strategies.
  • Home
  • Programming
    • Python course
  • Get in Touch
  • Cookie Policy
  1. Bestin-it.com – IT services and analytics for entrepreneurs
  2. Category: AI
🤖
Category

Category: AI

🤖 AI
7th June 2026 17 min

Qwen3.6-35B-A3B in practice: text, image, video and local API workflows

A practical guide to Qwen3.6-35B-A3B as one local multimodal model. See how to design prompts, call LM Studio or Ollama endpoints, and…
Read more #AMD W7900
🤖 AI
30th May 2026 10 min

Benchmark lab for local models: real 27B-35B results on one 48 GB GPU

A practical benchmark lab for local models on AMD PRO W7900 48 GB. Real tok/s, TTFT, disk size, VRAM after loading and…
Read more #AMD W7900
🤖 AI
27th May 2026 6 min

Multi-Token Prediction on AMD W7900: 1.85× speedup with llama-server Vulkan (Qwen3.6-35B benchmark)

We benchmark Multi-Token Prediction in llama-server (llama.cpp, Vulkan) on AMD PRO W7900. Real results: 49.7 → 91.8 tok/s, up to 2× on…
Read more #AMD W7900
🤖 AI
16th May 2026 15 min

Private AI Assistant for Productivity: How Freelancers and Managers Can Get Work Done in the Background

A practical English article on private AI assistants, background work, personal context, privacy, and real productivity gains for freelancers and managers.
Read more #AI agents
16th July 2025 29 min

GPT4All vs Jan – the battle for the best desktop LLM

The landscape of artificial intelligence has undergone a revolutionary transformation with the emergence of desktop Large Language Models (LLMs). As AI technology…
Read more
🤖 AI
10th July 2025 13 min

Ollama like Docker for AI

Remember when Docker revolutionized how we deploy applications? Well, Ollama is doing the same thing for AI models, and it’s changing the…
Read more
🤖
15th June 2025 37 min

Install llama.cpp on Windows 10 in 5 Steps

Introduction The landscape of artificial intelligence has dramatically shifted toward local inference, empowering developers and enthusiasts to run sophisticated language models directly…
Read more
14th June 2025 12 min

llama.cpp – The Core of the Offline Revolution

In the world of artificial intelligence, where cloud APIs and powerful GPU clusters dominate, one project is quietly revolutionizing how we run…
Read more
🤖 AI
7th June 2025 20 min

Private AI in Your Hands – Complete Guide to Offline LLM in 2025

The artificial intelligence revolution of recent years has been powered by massive language models running in the cloud. Services like ChatGPT, Claude,…
Read more
🤖 AI
3rd June 2025 25 min

Digital Independence Manifesto: AI Application Strategy for Small and Medium Enterprises

Introduction: The Era of Digital Dependency is Upon Us The technology world stands at a turning point that will define the next…
Read more

Categories

  • 3d printing (1)
  • AI (10)
  • Databases (2)
  • Games (1)
  • General (13)
  • IT Quarterly Review (5)
  • Machine learning (1)
  • PHP Laravel (5)
  • Python (9)
  • Tools (12)
  • Uncategorised (1)

Recent Articles

  • Qwen3.6-35B-A3B in practice: text, image, video and local API workflows
  • Benchmark lab for local models: real 27B-35B results on one 48 GB GPU
  • Multi-Token Prediction on AMD W7900: 1.85× speedup with llama-server Vulkan (Qwen3.6-35B benchmark)
  • Private AI Assistant for Productivity: How Freelancers and Managers Can Get Work Done in the Background
  • Describing PDF Charts with Vision Language Models
Bestin-it.com – IT services and analytics for entrepreneurs

IT Expert blog — practical articles on artificial intelligence, programming, project management and new technologies.

Categories

  • General 13
  • Tools 12
  • AI 10
  • Python 9
  • IT Quarterly Review 5
  • PHP Laravel 5
  • Databases 2
  • 3d printing 1
  • Machine learning 1
  • Games 1
  • Uncategorised 1

Recent Articles

  • Qwen3.6-35B-A3B in practice: text, image, video and local API workflows 7th June 2026
  • Benchmark lab for local models: real 27B-35B results on one 48 GB GPU 30th May 2026
  • Multi-Token Prediction on AMD W7900: 1.85× speedup with llama-server Vulkan (Qwen3.6-35B benchmark) 27th May 2026
  • Private AI Assistant for Productivity: How Freelancers and Managers Can Get Work Done in the Background 16th May 2026
  • Describing PDF Charts with Vision Language Models 8th May 2026
Artur Poniedziałek
Artur Poniedziałek IT Expert & Manager
  • Terms and Conditions
  • Privacy Policy
  • Get in Touch

© 2026 Bestin-it.com – IT services and analytics for entrepreneurs — IT Expert, AI & New Technologies

Privacy Policy Cookie Policy

Powered by WordPress & BestIn-IT Theme

🍪

We use cookies

We use cookies to improve your experience, analyse traffic, and show personalised ads. You can choose which categories to allow. Cookie Policy • Privacy Policy

Strictly Necessary Required for the website to function. Cannot be disabled.
Always on
Analytics Helps us understand how visitors use the site (Google Analytics 4).
Advertising Used to show relevant ads (Google AdSense). Enables personalised advertising.