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
16 articles

Turnbook: local memory for coding agents, without a single model call
Every conversation stored word for word in a SQLite file, with no model call at all: search runs on local embeddings and retrieval costs 3.1k tokens. 91.8% on LongMemEval, zero tokens to save.

Ollama voice: local speech synthesis, from the command line to the OpenAI API
Phonon brings speech synthesis to the Ollama server: one command to speak, an OpenAI-compatible endpoint and streaming read-aloud of the reply, 35% faster than the reference runtime on M5 Max.

SynthAPI: synthetic environments and scaling laws for training tool-use agents
Controlled synthetic environments with failures on a dial to train local tool-use agents: SynthAPI's scaling laws and the math — ~€1.60 of energy vs ~€158 of API for 10,000 tasks.

NVIDIA's Cosmos3-H-Dreams: real-time surgical simulation, and local robotics
A 15B world model that generates robotic surgery video in real time on a single GPU: what it changes for local robotics.

Cosmos3-Nano-Sim-Auto: NVIDIA's 16B world model that simulates driving in real time, on-premise
A 16B world model that generates up to 11 synchronized cameras and a LiDAR cloud: what it produces, how the loop closes, and what running it on-premise really means.

Secret Guard and local LLM gateways: protecting secrets while your agent uses them
Secret Guard is a Rust, open-source gateway that intercepts your agent's requests and swaps secrets for mocks before they reach the provider: the model never sees them, and the real value comes back to the agent.

On-device phone agents: what open mobile agents actually bring (after OpenMobile-2)
OpenMobile-2 opens up mobile agent training environments and recipes, and LFM3-1.7B shows a 1.7GB agent already runs on your phone: numbers, minimum requirements and honest limits.

Local text-to-SQL: query your business database without sending data to the cloud
A local model, the schema to the model, execution on your database: text-to-SQL in-house, ARCS benchmark numbers, and where it really breaks.

MOSS-Image: OpenMOSS-Team's ComfyUI ripack, workflows and real requirements
MOSS-Image: OpenMOSS-Team's ComfyUI ripack, ready in two folders. Real-world VRAM computed per weights combination, from ~11GB to ~31GB, plus the four included workflows.

Local Images: ComfyUI 0.40 and comfy_attention — new for all models
ComfyUI 0.40 extends comfy_attention to all models with per-model selectable kernels and LoRA override, turns on the asset system by default with a local API, and standardizes 3D output; the VRAM table stays the choice reference.

ML agents that run locally: MLExpert and EpochGo on Ollama, zero API costs
MLExpert raises the bar to 35B and a 72.7% medal rate; EpochGo runs three AutoML agents on 16 GB at zero API cost: what works today, the math and the limits.

MagpieTTS 357M: 12-language speech synthesis that runs on a laptop
NVIDIA releases MagpieTTS Multilingual, 364M parameters and 12 languages in one model: local text-to-speech with a 332 MB GGUF file, no GPU. The C++ runtime NeMo-Speech.cpp takes you from zero to first audio in three commands; the five voices are the same in every language, and for a natively Italian voice Piper is still ahead.

Decision models in local: JEV-35B and the 3B-active System 1
You don't need a big LLM to decide. JEV-35B (35B, 3B active) in NVFP4 on a 32GB GPU and ej (11.4MB) on CPU show how to do routing, classification and quality control without generating a single token.

Costs: local vs API, done with real numbers
How much does local really cost compared to a cloud API? Verified per-token prices, GPU amortization, electricity and the break-even point, calculated with real numbers.

Local AI for your business: 5 practical use cases
Five practical use cases of local AI for businesses: customer support, documents, internal search, CRM and generation — with the tools, minimum hardware and a 30-minute starting plan.

Privacy and GDPR: What Local AI Changes
Extra-EU transfers, sub-processors and Arts. 5, 25, 28, 32, 44: what the GDPR really says about cloud vs local, and what is still owed even with in-house AI.

