Local AI Deals

Cheapest box to run Gemma-3n-E4B at Q8_0

Google’s Gemma-3n-E4B is 6.8B parameters, dense. 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 38 hours ago
Quant
Context

Gemma-3n-E4B at Q8_0 needs 9GB.

Cheapest Config that fits: Mac mini, M6, 24GB. Fits, 12GB headroom. Est. 26.0 tok/s.

Best offer today: $1,299 at Best Buy — in stock, checked 38 hours ago.

Collecting price history — 3 of 90 days. No timing verdict yet.

Google names this model for its 4B effective parameters, but 6.8B raw weights are what you load, so the memory arithmetic uses 6.8B. The K/V figure accounts for layer sharing and sliding-window attention and is an estimate.

Offers — Mac mini, M6, 24GB, 512GB

  • Best BuyApple's own price, to the cent.in stockchecked 38 hours ago$1,299
  • Applelist pricein stockchecked 38 hours ago$1,299
  • ExpercomApple's own price, to the cent.in stockchecked 1 hour ago$1,299

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 = 6.8B × 1.063 B/param (8.5 bits) + 0.072 GB/1K × 8K K/V + 1.2 GB runtime
speed = bandwidth × 0.65 ÷ (4B active × 1.063 B/param) = 4.3 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, 24GB drops. One email, then we stop.

$1,299 is the lowest price we have recorded, rounded down to the dollar.

What else Mac mini M6 24GB runs

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

Bandwidth 170GB/s, usable memory 21GB of 24GB.