VPS Arena

Buy a box, or rent one?

14 reference machines people actually buy to run open models, against the cheapest VPS in the index with the same usable memory. Local hardware wins on speed (GPU-class bandwidth); a VPS wins on upfront cost and uptime. September 2026 — prices last checked 3 Sept 2026, refreshed weekly.

Reference machines for running open models locally. Memory, bandwidth and power come from vendor spec pages. Prices are refreshed weekly by scripts/update-hardware.ts: Apple prices are read from the Apple Store page (list price before tax; BTO memory upgrades add a curated delta, marked 'derived'); vendors that block automated fetches are checked through a web-search lookup and marked 'approximate' — those follow street prices, which in 2026 sit far above MSRP because of memory shortages. Prices are editable on the page — treat them as starting points.

MachinePriceMemory · usableBandwidthUp to 4B7–9B12–15B24–32B70B+Mixture-of-experts= VPS months
Raspberry Pi 5 (16 GB)

Raspberry Pi · sbc · ~8 W

$305vendor list price · 2 Sept 202616 GB · 14.5 GB17 GB/s19 moContabo 24 GB · $16.27/mo
GeForce RTX 5060 Ti 16 GB (card only)

NVIDIA · card only · ~180 W

$805street, approx. · 2 Sept 202616 GB · 15.5 GB448 GB/s50 moContabo 24 GB · $16.27/mo
Mac mini (M6, 16 GB)

Apple · desktop · ~35 W

$899vendor list price · 3 Sept 202616 GB · 12 GB153 GB/s103 moContabo 12 GB · $8.72/mo
GeForce RTX 5070 Ti 16 GB (card only)

NVIDIA · card only · ~300 W

$1,100street, approx. · 2 Sept 202616 GB · 15.5 GB896 GB/s68 moContabo 24 GB · $16.27/mo
Mac mini (M6, 32 GB)

Apple · desktop · ~35 W

$1,299vendor base + upgrade · 3 Sept 202632 GB · 24 GB153 GB/s80 moContabo 24 GB · $16.27/mo
GeForce RTX 5080 16 GB (card only)

NVIDIA · card only · ~360 W

$1,500street, approx. · 2 Sept 202616 GB · 15.5 GB960 GB/s92 moContabo 24 GB · $16.27/mo
Mac mini (M5 Pro, 24 GB)

Apple · desktop · ~50 W

$1,699vendor list price · 3 Sept 202624 GB · 18 GB307 GB/s104 moContabo 24 GB · $16.27/mo
Framework Desktop (Ryzen AI Max+ 395, 64 GB)

Framework · desktop · ~120 W

$1,959vendor list price · 2 Sept 202664 GB · 48 GB256 GB/s67 moContabo 48 GB · $29.05/mo
Mac mini (M5 Pro, 64 GB)

Apple · desktop · ~55 W

$2,299vendor base + upgrade · 3 Sept 202664 GB · 48 GB307 GB/s79 moContabo 48 GB · $29.05/mo
Mac Studio (M5 Max, 36 GB)

Apple · desktop · ~70 W

$2,499vendor list price · 3 Sept 202636 GB · 27 GB460 GB/s86 moContabo 48 GB · $29.05/mo
Framework Desktop (Ryzen AI Max+ 395, 128 GB)

Framework · desktop · ~120 W

$3,449vendor list price · 2 Sept 2026128 GB · 96 GB256 GB/s30 moContabo 96 GB · $115.06/mo
NVIDIA DGX Spark (128 GB)

NVIDIA · desktop · ~240 W

$4,699street, approx. · 2 Sept 2026128 GB · 96 GB273 GB/s41 moContabo 96 GB · $115.06/mo
GeForce RTX 5090 32 GB (card only)

NVIDIA · card only · ~575 W

$4,700street, approx. · 2 Sept 202632 GB · 31.5 GB1792 GB/s10+ yrsContabo 48 GB · $29.05/mo
Mac Studio (M5 Ultra, 96 GB)

Apple · desktop · ~110 W

$5,499vendor list price · 3 Sept 202696 GB · 72 GB1200 GB/s48 moContabo 96 GB · $115.06/mo
every model in the class fits some fit– none fit · “= VPS months”: hardware price ÷ the cheapest VPS with at least the machine's usable memory

Usable memory

Unified-memory machines (Apple, Strix Halo, DGX Spark) give the GPU about 75% of RAM by default; discrete cards lose ~0.5 GB to the driver; CPU-only boards keep 1.5 GB for the OS. Weights + KV cache must fit in what is left.

Why bandwidth decides speed

Generating a token reads every active weight once. An RTX 5090 at 1.8 TB/s streams an 8B Q4 model ~100× faster than a 4-vCPU VPS; a Mac mini sits in between. Per-model bands are on each model page.

2026 caveat

Memory-driven price rises have pushed GPUs 40–135% above MSRP and doubled the Raspberry Pi 5. Every model page has an editable calculator — plug in the price you can actually get.