Hardware & Infra: the chips, GPUs and data centres behind AI
Chips, devices and the infrastructure AI runs on.
Latest in Hardware & Infra
20 stories

Unified memory explained: Mac Studio vs RTX Spark vs a desktop GPU for local AI
Kelly B.

TPU vs GPU: what's the difference, and which one runs your AI?
Kelly B.

SSD and NAND prices in Q4 2026: why AI is now eating storage too
Kelly B.

Can you run an AI model bigger than your RAM? mmap and offloading, explained
Kelly B.

NVIDIA RTX Spark laptops: 128GB of unified memory on Windows, explained
Kelly B.

Why the RTX 5090 costs several times its $1,999 launch price right now
Kelly B.

PS6 and the memory crunch: why AI demand could push next-gen console prices up
Kelly B.

NVIDIA DSX POD explained: AI factories in a container, from six months to 14 days
Kelly B.

Mac Studio M5 Ultra with 512GB: what it means for running big AI models at home
Kelly B.

How much VRAM do you need to run an LLM locally? The simple math
Kelly B.
Hardware & Infra desk
Chips, devices and the infrastructure AI runs on.
Editor's picks
- What is MCP? The Model Context Protocol explained for vibe codersBuildCodema Editorial ·
- What are agent skills? How to write your first SKILL.mdAICodema Editorial ·
- Git and GitHub basics for vibe coders: never lose AI-written codeBuildCodema Editorial ·
- How much VRAM do you need to run an LLM locally? The simple mathHardware & InfraKelly B. ·
- What is an agent harness? Google's Harness² shows why it matters as much as the modelAIJohn F. ·
Codema Daily
Codema Daily
A short daily note on AI, building, hardware and AI money.
Nothing is saved yet. Email delivery is not connected, so this form does not store your address.


