Local AI Deals

Cheapest box to run Llama-4-Scout-17B-16E at BF16

Meta’s Llama-4-Scout-17B-16E is 109B parameters, 17B 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 10 hours ago
Quant
Context

Llama-4-Scout-17B-16E at BF16 needs 221GB.

Cheapest Config that fits: Mac Studio, M5 Ultra, 256GB. Fits, 27GB headroom. Est. 17.6 tok/s.

Best offer today: $9,499 at Apple in stock, checked 10 hours ago.

Collecting price history — 2 of 90 days. No timing verdict yet.

Offers — Mac Studio, M5 Ultra, 256GB, 1TB

  • Adoramaout of stockchecked 10 hours ago$9,499
  • Applelist pricein stockchecked 10 hours ago$9,499
  • B&H Photoout of stockchecked 10 hours ago$9,499

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 = 109B × 2.000 B/param (16 bits) + 0.197 GB/1K × 8K K/V + 1.2 GB runtime
speed = bandwidth × 0.5 ÷ (17B active × 2.000 B/param) = 34.0 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 Studio, M5 Ultra, 256GB drops. One email, then we stop.

Pre-filled at the lowest price we have recorded, $9,499.

What else Mac Studio M5 Ultra 256GB runs

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

Bandwidth 1.2TB/s, usable memory 248GB of 256GB.