Resource center

Guides to understand AI

From concept to hardware: everything you need to run AI yourself, locally or in the cloud, without breaking the bank.

Local AI vs cloud AI: which should you choose?

Privacy, cost, performance: we compare local inference vs cloud API to help you decide.

From a classic VPS to hourly spot GPUs: the guide to AI infrastructure without buying hardware.

The difference between an LLM, a foundation model, a fine-tune, quantization, and what an evaluation “harness” actually is.

GPU, RAM, NVMe vs SATA SSD: how to size a machine for inference and fine-tuning.

Threadripper, Mac Studio, multi-GPU: pro configurations to push local AI to its maximum.

Hyped or outdated? We separate myth from reality on the Mac mini as an AI inference station.

NVIDIA DGX Spark, Strix Halo, Mac mini M4: three opposing philosophies for local AI in 2026. VRAM, bandwidth, price, use cases.

Reliable function calling, stronger steerability, agentic loops: what Hermes 2.3 really brings and how to use it locally or via API.

lm-eval, lighteval, OpenCompass: without an evaluation harness you're picking a model at random. The guide to succeeding at an AI project.

Grok, ChatGPT, Claude, Gemini, Muse, Le Chat, DeepSeek, Perplexity: strengths, weaknesses, pricing and use cases of every major AI assistant in 2026.