PerGB

NVIDIA RTX 5000 Ada

Live eBay prices, cheapest first. The best one right now is $5,499 (new).

Specs

VRAM
32 GB GDDR6
Bandwidth
576 GB/s
FP32
65.3 TFLOPS
FP16
261 TFLOPS
Power
250 W
Connector
PCIe 4.0
Released
2023
Launch price
$4,000
CUDA compute
8.9
Llama 3.1 8B at Q4 (est.)
59–89 tokens/s

Price right now

Live on eBay
Lowest now$5,499
Median ask$7,038
Per GB VRAM$171.84
vs launch price37% over
Live listings19

From the live listings below; shipping included.

Listings

Live on eBay
ListingConditionPriceChecked
New$5,499−22%+$52.00 shipping
New$5,678−19%+$52.00 shipping
New$5,721−19%+$220.35 shipping
Open box$6,314or best offer−10%free shipping
New$6,549−7%free shipping
New$6,599or best offer−6%free shipping
New$6,850or best offerfree shipping
New$6,895+$57.00 shipping
New$7,004+$26.00 shipping
Open box$7,038or best offerfree shipping
Open box$7,185or best offerfree shipping
Open box$7,185or best offerfree shipping
Open box$7,185or best offerfree shipping
Open box$7,185or best offerfree shipping
Open box$7,185or best offerfree shipping
Open box$7,185or best offerfree shipping
Open box$7,185or best offerfree shipping
Open box$7,550or best offer+$50.00 shipping
New$7,640+$49.90 shipping

Auctions ending soon

No auctions ending soon right now.

Prices include shipping and were read from eBay at the time shown. They can change: check the listing before you buy.

Owner reviews

No owner reviews yet. Own one? Tell others how it runs.

From signed-in owners, checked before they're published. PerGB doesn't pay for or edit reviews.

How it compares

Live on eBay

As much VRAM, about as fast, for less

Faster, for the least

More VRAM, for not much more

From the live listings of every GPU, shipping included; performance against the GeForce RTX 3090 (FP16 or FP32 compute and memory bandwidth). Updated with every build.

Local AI: what it runs

Model (Q4, 8K context)RTX 5000 Ada neededCosts nowSpeed (est.)
Llama 3.1 8B1 card$5,49959–89 tokens/s
Qwen3 14B1 card$5,49932–48 tokens/s
gpt-oss 20B1 card$5,49979–119 tokens/s
Gemma 3 27B1 card$5,49917–26 tokens/s
Qwen3 32B1 card$5,49914–22 tokens/s
Llama 3.3 70B2 cards$11,1776.7–10 tokens/s
gpt-oss 120B3 cards$16,89856–84 tokens/s
Qwen3 235B-A22B5 cards$29,76113–19 tokens/s
DeepSeek R1 / V3 671Bmore than 8——

Cost: that many of the cheapest live listings. Speed: an estimate from the memory bandwidth for one person chatting. Try other models, sizes and contexts.

Decision models

Model (Q4, 8K context)RTX 5000 Ada neededCosts nowPer question (est.)
Julia-10.144B1 card$5,4995.1–11 ms
Laya0.421B1 card$5,4998.5–18 ms
Kev-4B4B1 card$5,49921–44 ms
lev4B1 card$5,49962–132 ms
OpenJev27B1 card$5,49973–157 ms
Clef27B1 card$5,49973–157 ms
Perplexity Decider v1.227B1 card$5,49973–157 ms
mammoth-127B1 card$5,49973–157 ms

Decision models score the options you give them instead of writing text, so they're timed per question. The time is scaled from each model's reported speed on an RTX PRO 6000 by this card's compute and memory bandwidth, within about half either way. About the models.

Compare elsewhere

Search other shops for NVIDIA RTX 5000 Ada. These open the shop's own search; we don't show their prices here.