Which Darkbloom model should I run on my Mac?
Updated
Short answer: run Gemma 4 26B (QAT 4-bit) on its own as your steady earner if your Mac has 32 GB or more, keep gpt-oss-20b as the fallback, and try a large Qwen (Qwen3.5 or Qwen3.6 35B, 36 GB and up) when its demand spikes. On a 64 GB Mac every current model fits. 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 BloomGauge.
Three kinds of model
- Steady earners. Gemma has carried most of the paid work on our test Mac (about 82% of its token revenue in September). Run a steady earner 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.
Gemma needs the Mac to itself
Darkbloom’s open-source coordinator treats Gemma 4 as a dedicated model by default: public Gemma requests only go to Macs whose whole advertised model list is Gemma 4. A Mac that advertises Gemma plus any other model gets no public Gemma traffic, even while Gemma is loaded. Darkbloom hasn’t said whether production uses a different setting, but providers’ reports match this rule. If you run Gemma, run it alone.
Which models fit, by memory
Free memory needed when the model loads, and the smallest Mac where it loads with nothing else running, from Darkbloom’s hardware requirements (September 2026). Re-check with darkbloom models catalog, because the catalog changes.
| Model | Free memory at load | Smallest Mac |
|---|---|---|
| gpt-oss-20b | 18.0 GiB | 24 GB (tight) |
| Gemma 4 26B (QAT 4-bit) | 23.9 GiB | 32 GB |
| Qwen3-VL 30B A3B | 27.0 GiB | 32 GB (tight) |
| Qwen3.5 35B A3B | 29.9 GiB | 36 GB |
| Qwen3.6 35B A3B | 30.3 GiB | 36 GB |
| Gemma 4 26B (8-bit) | 37.8 GiB | 48 GB |
What to run, by memory
- 24 GB: gpt-oss-20b, kept loaded for the base reward. Larger Macs win most requests.
- 32–36 GB: Gemma 4 26B QAT on its own is the usual choice; Qwen3.5 35B fits from 36 GB.
- 48 GB: every 4-bit model fits. Run Gemma 4 26B alone as the steady earner, and try a large Qwen when its demand spikes.
- 64 GB and up: the same choice, with room to keep a second model ready for switching. Remember that Gemma only gets public work when it is the only model the Mac advertises.
- New providers: Darkbloom’s setup page (September 2026) asks for 48 GB or more of memory and macOS 26 or later.
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 BloomGauge helps
With Manager on, BloomGauge holds the model that has paid best on your Mac over the last 30 days (or, on a new Mac, what pays best on Macs with the same chip and memory), and moves only when at least five Macs like yours have clearly earned more on another model for two hours.
Questions
What is the best Darkbloom model to run?
It changes with demand and with your Mac. Gemma has been the steadiest earner on Macs with 36 GB or more (run it alone, because Gemma traffic only goes to Gemma-only Macs), large Qwen models pay well during demand spikes, and gpt-oss is a dependable fallback when the others are quiet.
Which Darkbloom model should I run on a 64 GB Mac?
Every current catalog model fits on 64 GB. Gemma 4 26B, run on its own, has been the steadiest earner; large Qwen models pay more during demand spikes; gpt-oss-20b is the fallback. Compare what each actually pays on your Mac over a few days, or let a manager such as BloomGauge do it.
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
- How much can a Mac earn on Darkbloom?
- Darkbloom on a Mac Studio: what Max and Ultra Macs earn
- Darkbloom model won’t load: not enough memory
- Can you run several Darkbloom models at once?
- BloomGauge vs. darkbloom-manager
- Darkbloom model prices: what each model pays per million tokens
Updated 2026-09-29. Still stuck? Ask in #bloomgauge on the Darkbloom Slack or contact us. BloomGauge is independent and not affiliated with Darkbloom.