Blog
Articles, guides, and insights on local artificial intelligence
Reading paths
Local speech
From microphone to synthesizer: local STT and TTS, voice pipelines and the models that make your machine speak.
3 articles in this path · 16 min read
Start here
The in-order path for newcomers to local AI: from basic concepts to installation and your first model.
5 articles in this path · 29 min read
Optimize performance
Pick the right hardware and get the most out of what you already own: CPU vs GPU, Mac, Raspberry Pi, and fast serving.
13 articles in this path · 83 min read
Data and privacy
What actually goes over the network with local AI: the data, the security, the compliance, and the control that stays in your hands.
3 articles in this path · 19 min read
Choosing hardware and model
How to pick the right hardware and the model suited to your use: VRAM, quantization, GPU or CPU and response speed.
19 articles in this path · 126 min read
Robotics and world models
Local world models for robotics: driving simulation, edge policy and real-time surgical simulation.
3 articles in this path · 22 min read
Local agents
Agents that run locally: inference frameworks, secure gateways and synthetic-data training. Articles on tool-use agents, API costs and key security.
5 articles in this path · 31 min read
11 articles

Enterprise agents with open-weight models: Gartner's cost report, the math and the 90% rule
The Gartner report (November 2026): 90% of an enterprise agent's steps on open-weight models, at one fifth of a frontier's cost. The three key numbers, the assumptions, and when it's really worth it.

Yzma: embeddings up to 2.6x faster than Ollama, the comparison
Yzma calls llama.cpp in the same process: no server, no round trip. It is 2.6x faster than Ollama on embeddings — with the numbers, the math and the setup.

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.

Cosmos 3 Edge: the DROID policy for robotics that runs on the edge
Cosmos3-Edge-Policy-DROID: NVIDIA's 4B robotic policy. How much hardware you need to run it in real time on a Jetson, and where it stops.

Frontier vs local AI: the honest comparison nobody makes
Frontier models are still more powerful on complex cases, but cost is the last thing that decides: the table, the break-even point and the honest answer to "front-load and then ride for free?".

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.

Qwen3.8-27B vs Gemma 4 26B A4B: the new frontier at 24GB
A 27.8B dense or a MoE with 3.8B active, a 262K context against 256K and almost the same weight at Q4_K_M: two opposite ways of putting big-model quality on a 24GB consumer card. Which is faster, which goes deeper, and when to pick one over the other.

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.

Mistral vs Gemma: Light Models Compared
Full comparison of the Mistral and Gemma open model families: sizes, required VRAM, context, supported languages and licenses, with a practical method for picking the right model for your hardware.

Ollama vs LM Studio: Which Tool to Choose
Ollama for servers and scripts, LM Studio for desktop exploration: the comparison table, the two APIs (11434/1234) and the real case of using both.

