readygpu: hardware for local AI

Live UK, Germany, Canada and US prices for GPUs and Macs that run open AI models. No sign-up.

ดูบน readygpu.com

เซิร์ฟเวอร์ MCP แบบโฮสต์

npx add-mcp 'https://readygpu.com/api/mcp'

ติดตั้งลง Claude Code, Codex, Cursor และอื่นๆ

เอกสาร

US prices · checked 2 min ago

Plan a

local AI machine

See which GPUs, Macs and mini PCs run the models you want, how fast they run them, and what they cost at retailers in the US today.

Start a buildRun a specific model →What can my hardware run? →

Top pick for coding at 32k

#1 of 2

RTX 5060 Ti 16GB entry box

PC · 16 GB · 448 GB/s

53tok/sest.

gpt-oss 20BQ4_K_M

Total

$1,637

  • Chat 15+(fast enough)
  • Coding 20+(fast enough)
  • Agents 30+(fast enough)

Memory12.5 / 15.4 GB

  • Weights 10.8
  • KV cache 0.8
  • Runtime 0.9
  • Free 2.9

See all 2 builds in $1,000–2,000 ↓

Featured builds

Ranked by the best model each one runs fast enough for coding, at 32k context.

#BuildBest model for codingSpeed @32kMemory usedTotal

  1. 1
    RTX 5060 Ti 16GB entry box
    PC · 16 GB · 448 GB/s
    gpt-oss 20BQ4_K_M
    53tok/sest.
    Memory12.5 / 15.4 GB
    $1,637
    View
  2. 2
    Used RTX 3060 12GB starter
    PC · 12 GB · 360 GB/s
    Gemma 4 12BQ6_K
    21tok/sest.
    Memory10.8 / 11.4 GB
    $1,154
    View

What runs where

Every popular model against every machine, at 32k context. Each cell is the estimated speed in tokens per second.

  • 30+ tok/s, fast enough for agents
  • 15 to 30, fine for chat and coding
  • Under 15, fits but slow
  • Spills into system RAM
  • Won't run
ModelRTX 5060 Ti 16GB16 GBRTX 5070 Ti16 GBRTX 309024 GBRTX 409024 GBRTX 509032 GBMac mini M4 Pro 64GB64 GBMac Studio M4 Max 128GB128 GB
Gemma 4 26B-A4BUD-Q4_K_M · 4B active31offload44offload991071903061
Qwen 3.8 27BUD-Q4_K_M9offload11offload313359919
Gemma 4 31BQ4_K_M6offload7offload272951816
GLM 4.5 AirQ4_K_M · 13.5B activewon't runwon't runwon't runwon't runwon't runwon't run14
gpt-oss 120BMXFP4 · 5.8B activewon't runwon't runwon't runwon't runwon't runwon't run49
Mistral Small 4 119BUD-Q4_K_M · 7.1B activewon't runwon't runwon't runwon't runwon't runwon't run42
Nemotron 3 Super 120B-A12BUD-Q4_K_M · 12B activewon't runwon't runwon't runwon't runwon't runwon't run25
Qwen 3.5 122B-A10BQ4_K_M · 10B activewon't runwon't runwon't runwon't runwon't runwon't run30

Estimates from memory bandwidth and model size, not measurements. How estimates work

Popular GPUs

Compared on Qwen 3.8 27B at 32k context, the model people ask about most.

GPUVRAMBandwidthQwen 3.8 27B @32kPriceActions
NVIDIA GeForce RTX 3090nvidia24 GB936 GB/s31tok/sest.$1,698Amazon $1,698eBay $1,999Add
NVIDIA GeForce RTX 5090nvidia32 GB1,792 GB/s59tok/sest.$4,921eBay $4,921Amazon $7,499Add
NVIDIA GeForce RTX 4090nvidia24 GB1,008 GB/s33tok/sest.$2,073eBay $2,073Amazon $3,600Add
NVIDIA GeForce RTX 5070 Tinvidia16 GB896 GB/soffload11 tok/sest.$995eBay $995Amazon $1,260Add
NVIDIA GeForce RTX 5060 Ti 16GBnvidia16 GB448 GB/soffload9 tok/sest.$618eBay $618Amazon $750Add
AMD Radeon RX 7900 XTXamd24 GB960 GB/s28tok/sest.$1,200Amazon $1,200eBay $2,312Add
NVIDIA GeForce RTX 3060 12GBnvidia12 GB360 GB/soffload5 tok/sest.$370Amazon $370eBay $400Add
AMD Radeon RX 9070 XTamd16 GB640 GB/soffload9 tok/sest.$850Amazon $850eBay $900Add

New this week

The catalogue updates every day as models, hardware and prices change.

New models

New hardware

Price drops

More hardware for local AI

Already own a GPU?

Pick your card, Mac or mini PC and see every model it runs, at every context length, before you spend anything on an upgrade.

Check my hardwareBrowse used GPUs

  • Graphics cards
  • Macs
  • Mini PCs