Every tool I’ve tested
Ordered newest first. Each review ran the same core set of prompts — long doc summarisation, a coding task, a hard reasoning question, image understanding and cost per run — so scores are comparable.
One email a week
What I tested this week, what it cost to run, and the one thing worth your time. No spam, unsubscribe in one click.
Cloud models
DeepSeek V4 Pro
The paid one I reach for when a job spans more than one file.
Worth paying for on the jobs that go live. Not worth using for a one-line fix, where the local model is free and fast enough.
DeepSeek V4.1 Flash
Cheap, fast, and good enough for most of the work I used to think needed a big model.
My default for everyday work. Switch up to V4 Pro the moment a task crosses a file boundary or goes live.
Local models
Qwen 3.8 27B (24K, no thinking)
The free one. Fits entirely on a 16 GB card at 24K context with thinking turned off.
If the task fits in one file, start here. It costs nothing and it is fast. Move up only when it visibly struggles.
Qwen 3.8 27B (32K, thinking on)
Same model, more context, thinking switched on. Slower, and the extra room costs you speed.
Keep it installed for hard questions you cannot send off the machine. For everything else the 24K tag is the better trade.
Apps & managers
OpenCode
The agent that runs both the free local model and the paid cloud models from one place.
The best free way to use one paid model and one local model without maintaining two setups. It is the first thing I install on a new machine.
Ollama
The least interesting part of the local setup, which is exactly why it works.
Boring in the right way. Install it, pull a model that fits your card, and stop thinking about the runtime.