Blog
Articles, guides, and insights on local artificial intelligence
10 articles found per "inferenza"

Mistral Large 4 in open weights: a 1T MoE (52B active) for on-premise inference
Mistral released Large 4 in open weights (1.03T total, 52B active, 1M context, open-weight license): an article teaching how to read MoE specs and do the RAM, quantization and speed math for on-premise inference.

ML Drift: Google's open-source on-device GPU engine, and when it beats the generalists
The engine that runs models inside Chrome and YouTube is now open source: architecture, benchmark numbers, and an honest comparison with Ollama and llama.cpp.

Mac Studio M5 Ultra: 512GB of unified memory on the desktop
Four dies, 512GB of unified memory at 1.2 TB/s: the Mac Studio M5 Ultra runs 100-560B MoE models locally. The speed math, the cost comparison with the DGX Station, and when the Mac is the right choice.

What a token costs: five routes, the math, and the break-even point
Frontier API, subscription, inference providers, rented GPU or your own hardware: five routes to tokens, with real monthly costs, the electricity bill, and the calculated break-even point.

NVIDIA, AMD and Intel for local AI: which platform to choose
CUDA, ROCm or Vulkan? We compare the three local-AI platforms based on what is actually available: official software stacks, cards by VRAM tier (12, 16 and 24GB) and real speeds. Where the obvious choice remains, where AMD wins on value, and when it makes sense to leave NVIDIA.

The 16GB Blackwell cards: 5060 Ti, 5070, 5070 Ti
The 16GB VRAM tier is the center of gravity of local AI in 2026. It's enough memory to run the best open dense models in Q4 formats — the 27B class, the new balance point of the open catalog — without giving up too much context, and a list price that (depending on the month) stays within a personal budget. The Blackwell generation offers three cards exactly in the middle of this tier: the RTX 5060 Ti, 5070 and 5070 Ti. Same generation, same GDDR7, three very different experiences. Here's how they compare: what each one really brings you, and where your budget should go.

Ollama vs llama.cpp: under the hood
Ollama runs llama.cpp under the hood, but the two are not the same thing: one is the engine, the other the car. What's really underneath, when the difference matters, and how to choose without slogans.

A Model Without a GPU: When the CPU Is Actually Enough
In 2026, CPU-only inference is no longer a fallback: when it genuinely works, what speed to expect, and which levers to pull to squeeze the most out of your processor.

KV cache: why your RAM needs more than just the model
What the KV cache is, the formula to calculate it with real numbers from Llama 3.1 8B and Qwen3 8B, and the three levers to manage it: context, quantization and flash attention.

GPU or CPU: when the CPU is enough
How prefill and decode work, what matters for speed (memory bandwidth), real numbers on a mainstream laptop, the cases where the CPU is enough and where VRAM is needed — with the commands to measure.

