Mac mini M6: 16GB vs 24GB for local AI
The Mac mini M6, 24GB holds 13 of the 39 open models here, and the Mac mini M6, 16GB holds 10. The Mac mini M6, 16GB costs $200 less. On Gemma 4 12B, the strongest model both hold, the Mac mini M6, 24GB is about 1.1× faster: 16 tok/s against 14, both estimated from memory bandwidth. The Mac mini M6, 16GB pays for itself sooner, in 71 years against 85 years at 500k tokens a day.
| Mac mini M6, 16GB | Mac mini M6, 24GB | |
|---|---|---|
| Price | $899 | $1,099 |
| Memory | 16 GB | 24 GB |
| Usable by the GPU | 10.5 GB | 16 GB |
| Memory bandwidth | 153 GB/s | 170 GB/s |
| Power under load | 65 Wstand-in | 65 Wstand-in |
| Models that fit | 10 | 13 |
| Best model it runs | Gemma 4 12B | Gemma 4 12B |
| Speed on that model | 14 tok/s estimated | 16 tok/s estimated |
| Pay-back on that model | Pays back in 71 years | Pays back in 85 years |
Neither power figure above is measured on the machine beside it. Both are stand-ins borrowed from the nearest hardware the data does have, so what the row shows is one borrowed figure printed twice. Each machine's page names the figure it borrows and why. Every pay-back figure on this page prices its electricity from these numbers.
Run the numbers on the Mac mini M6, 16GB · or the Mac mini M6, 24GB
How much use it takes to pay back
Everything above is at 500k tokens a day. Pay-back moves with how much you actually run, so here are both machines on Gemma 4 12B, the strongest model both hold, at the five levels of use the calculator names. The Mac mini M6, 16GB pays back sooner at every level of use, so this is not a choice that turns on how hard you work it.
| A day's use | Mac mini M6, 16GB | Mac mini M6, 24GB |
|---|---|---|
| 50ka few chats a day | 706 years | 846 years |
| 200klight assistant use | 176 years | 212 years |
| 1Ma moderate coding-assistant day | 35 years | 42 years |
| 4Mheavy coding with an agent | 8.8 years | 11 years |
| 20Magents running most of the day | 21 monthsits ceiling | 2.1 years |
On Gemma 4 12B the Mac mini M6, 16GB generates at most 19.8M tokens a day, so its figure at 20M tokens a day is for the most it can do, not for the whole of what was asked.
Run the Mac mini M6, 16GB at 20M tokens a day · or the Mac mini M6, 24GB
What the extra memory buys
The Mac mini M6, 24GB holds 3 models the Mac mini M6, 16GB cannot at 32k of context. The strongest of them are what the difference in memory actually buys.
| Model | Weights | Needs at 32k | On the Mac mini M6, 24GB |
|---|---|---|---|
| Granite 4.2 8BBelow every hosted tier | 5.3 GB | 11 GB | 12 tok/s estimated |
| gpt-oss-20bBelow every hosted tier | 12 GB | 13 GB | 18 tok/s estimated |
| Ministral 3 14BBelow every hosted tier | 8.2 GB | 14 GB | 9.4 tok/s estimated |
The assumptions behind both columns
Both columns use the same usage: 500k tokens a day at 15:1 input to output, 32k of context, $0.17 per kWh, and today's API prices held flat. Speeds marked estimated are worked out from memory bandwidth rather than measured, and pay-back scales with them. Graphics cards are priced as the card alone, so add the PC around one before comparing it with a complete computer. Change any of it in the calculator.
More head to head: everything the Mac mini M6, 16GB runs · everything the Mac mini M6, 24GB runs · every other match-up · the quickest pay-back at each level of use · every model against the frontier