Local AI Deals

Cheapest box to run Gemma-4-26B-A4B at Q6_K

Google’s Gemma-4-26B-A4B is 25.2B parameters, 3.8B of them read per token. The number below is computed from that and each vendor’s published specs, not asserted. Switch the quant or the context and it recomputes in place.

Fit finderprices checked 32 minutes ago
Quant
Context

Gemma-4-26B-A4B at Q6_K needs 22GB.

Cheapest Config that fits: Mac mini, M6, 32GB. Fits, 7GB headroom. Est. 27.3 tok/s.

Best offer today: $1,499 at Apple — in stock, checked 32 minutes ago.

Price history: 34 days recorded.

The 26B in the name is marketing; Google's own table reads 25.2B total and 3.8B active, and that is what we publish. Only the 5 global-attention layers cache unboundedly; the rest slide a 1024-token window.

Offers — Mac mini, M6, 32GB, 512GB

  • ExpercomSold out.out of stockchecked 28 days ago$1,499
  • Applelist pricein stockchecked 32 minutes ago$1,499
  • B&H PhotoPreorder, ships about 22 Sep.out of stockchecked 33 days ago$1,599

GeForce RTX 5090 is a card, not a computer: every price shown for it is the cheapest listing we found plus $1,000 for the minimum host machine.

memory = 25.2B × 0.820 B/param (6.56 bits) + 0.042 GB/1K × 8K K/V + 1.2 GB runtime
speed = bandwidth × 0.5 ÷ (3.8B active × 0.820 B/param) = 3.1 GB read per token
usable = memory − operating system reserve (8% on a Mac, 6% on a DGX Spark, 4% on a card)

Bandwidth is the vendor’s published figure. Every speed is an estimate and says so. Methodology.

Email me when Mac mini, M6, 32GB drops. One email, then we stop.

$1,499 is the lowest price we have recorded, rounded down to the dollar.

What else Mac mini M6 32GB runs

Best quant that still fits at 8K context, largest model first. Full list on the Config page.

Bandwidth 170GB/s, usable memory 29GB of 32GB.