Local AI Deals

Cheapest box to run DeepSeek-V3 at Q4_K_M

DeepSeek’s DeepSeek-V3 is 671B parameters, 37B 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 9 hours ago
Quant
Context

DeepSeek-V3 at Q4_K_M needs 407GB.

Cheapest Config that fits: Mac Studio, M5 Ultra, 512GB. Fits, 97GB headroom. Est. 26.9 tok/s.

No price yet: Ships late October 2026. Apple has not published a price.

Collecting price history — 1 of 90 days. No timing verdict yet.

Offers — Mac Studio, M5 Ultra, 512GB, 1TB

Ships late October 2026. Apple has not published a price.

GeForce RTX 5090 is a card, not a computer: its price is the US street median plus $1,000 for the minimum host machine. NVIDIA's $1,999 MSRP is not a price anyone pays.

memory = 671B × 0.604 B/param (4.83 bits) + 0.070 GB/1K × 8K K/V + 1.2 GB runtime
speed = bandwidth × 0.5 ÷ (37B active × 0.604 B/param) = 22.3 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 Studio, M5 Ultra, 512GB is back in stock. One email, then we stop.

No account. One-click unsubscribe in the email.

What else Mac Studio M5 Ultra 512GB runs

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

Bandwidth 1.2TB/s, usable memory 504GB of 512GB.