Which Darkbloom model should I run on my Mac?
What a model pays depends on how many people are asking for it right now and how many other Macs already serve it. That changes through the day, so there is rarely one right answer for long. These rules of thumb come from weeks of Darkbloom history measured by Bloomkeeper.
Three kinds of model
- Steady earners. Models like Gemma and Nemotron have carried most of the paid work on our test Mac. Run one of these most of the time.
- Spike models. Large Qwen models get occasional rushes of paid requests, and can pay more than $0.30 an hour while a rush lasts, then go quiet.
- Fallbacks. gpt-oss almost always has some demand. It usually pays less, but beats sitting idle when the main earners fade.
Memory decides what fits
The model has to fit in your Mac’s unified memory next to everything else. macOS keeps the last model’s files in its file cache and Darkbloom counts that as in use, so a large model can refuse to load right after a switch even though it would fit. Clearing the file cache (sudo purge) before loading fixes that.
Measure it on your own Mac
Pay depends on your chip, memory and how many other providers serve the same model, so numbers from someone else’s Mac only go so far. Run a model for a few hours at different times of day before you decide it doesn’t pay.
How Bloomkeeper helps
Bloomkeeper’s optimizer does this for you: it keeps your best earner running, switches to a spike model while demand lasts, falls back to a steady model when earners go quiet, and spends a little time each day measuring other models so it knows where to go next.
Questions
What is the best Darkbloom model to run?
It changes with demand. Steady earners such as Gemma and Nemotron are a good default, large Qwen models pay well during demand spikes, and gpt-oss is a dependable fallback when the others are quiet.
Why won’t a large Darkbloom model load on my Mac?
Often because macOS is still holding the previous model’s files in its file cache, which Darkbloom counts as used memory. Clearing the cache with sudo purge before loading usually fixes it; otherwise the model is too large for your Mac’s memory.
Related
Updated 2026-09-26. Still stuck? Ask in #bloom-dash-optimizer on the Darkbloom Slack or contact us. Bloomkeeper is independent and not affiliated with Darkbloom.