Local AI Deals

Mac mini, M6, 32GB vs GeForce RTX 5090, 32GB

Both hold Gemma-3-27B at Q6_K. GeForce RTX 5090, 32GB decodes an est. 52.6 tok/s against 5.0, and costs $1,500.99 more — $31.52.03628948117239 per extra token per second. Worth it if you read the output as it arrives; not if you queue jobs.

For Gemma-3-27B at Q6_KMac mini 32GBRTX 5090 32GB
Fit
Tight
Fits
Headroom
4GB
5GB
Est. speed
5.0 tok/s
52.6 tok/s
Cheapest today
$1,499 at Apple
$2,999.99 at Best Buy
Per GB of memory
$47
$94
Memory
32GB unified memory
32GB GDDR7 memory
Usable for a model
29GB
31GB
Memory bandwidth
170GB/s
1.8TB/s
Storage
512GB
Lowest recorded
$1,499 in 2d
$2,999 in 1d

Fit, headroom and speed are computed from each vendor’s published bandwidth and the model’s own size at 8K context. Prices are the cheapest listing we could read on each seller’s page. The arithmetic is here.

Where they actually differ

Every model we track at Q6_K. The rows where the two boxes agree are dimmed, because they are not what you are choosing between.