Local AI Deals

Cheapest box to run Devstral-Small-2507 at Q8_0

Mistral’s Devstral-Small-2507 is 24B 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 35 hours ago
Quant
Context

Devstral-Small-2507 at Q8_0 needs 28GB.

Cheapest Config that fits: Mac mini, M5 Pro, 48GB. Fits, 16GB headroom. Est. 7.8 tok/s.

Best offer today: $2,499 at Apple in stock, checked 35 hours ago.

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

Offers — Mac mini, M5 Pro, 48GB, 512GB

  • Applelist pricein stockchecked 35 hours ago$2,499

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 = 24B × 1.063 B/param (8.5 bits) + 0.164 GB/1K × 8K K/V + 1.2 GB runtime
speed = bandwidth × 0.65 ÷ (24B active × 1.063 B/param) = 25.5 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, M5 Pro, 48GB drops. One email, then we stop.

$2,499 is the lowest price we have recorded, rounded down to the dollar.

What else Mac mini M5 Pro 48GB runs

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

Bandwidth 307GB/s, usable memory 44GB of 48GB.