What I
use.
Updated 14 September 2026
Below is the hardware and software I use. For local model tests, I use the DGX Spark; how I run local LLMs on it
01Hardware
Local model tests
DGX Spark
- Memory
- 128 GB unified
- Compute
- Grace Blackwell
- Purpose
- Local models + evals
- Location
- Hoorn
- Models
- Gemma-4 · Nemotron-3
On the go
MacBook Air M3
- Memory
- 8 GB
- OS
- macOS
- Use
- Web work + writing
- Vibe
- Light and quiet
At home
Mac mini M2
- Memory
- 16 GB
- Screens
- 2× 4K
- Keyboard
- Apple Magic Keyboard
- Mouse
- Apple Magic Mouse
- Desk
- Sit-stand
Audio
For calls and recordings
- Microphone
- Rode PodMic
- Setup
- Desk mat + arm
- Status
- Works fine
02Software
Coding
Editor & terminal
- Editor
- VS Code (→ Cursor todo)
- Terminal
- Apple Terminal
- AI pair
- Claude Code · Opus 4.8
- Plan
- Anthropic Max
- Theme
- Default, no time for it
AI / ML
Models & stack
- Hosted
- Anthropic Claude
- Daily
- ChatGPT for simple work
- Local
- Gemma-4-26-4b-it
- Embeddings
- Qwen-Embedding-4B
- Search
- PGVector
- Tools
- MCP servers where they fit
Development
Languages & frameworks
- Backend
- Python (pip + uv)
Ruby - Frontend
- TypeScript (npm)
- Frameworks
- Next.js · Vue · Astro
Ruby on Rails - Data
- Supabase · Prisma
- React stack
- Remix / RR v7
- Namesake
- Django (yes, literally too)
Infra
Hosting & ops
- Apps
- Vercel · Fly.io
- Domains
- TransIP
- Edge
- Vercel + Supabase
- This blog
- TransIP + GHA
- Side bot
- Pi 5 with OpenClaw
03What I no longer use
Dropped
Cloud GPUs for benchmarks
With cloud GPUs, I saw too much variation between runs. Since getting the Spark, I run benchmarks on the same machine to make conditions easier to compare.
Dropped
Tooling chase
I spend less time comparing editors, adjusting themes and maintaining dotfiles. I change my tools when something gets in the way of my work.
Dropped
Notion and heavy doc tools
I keep notes in Markdown in a repository, so the text and its version history stay together.
Missed something or questions about a choice? Send a message.