PerGB

NVIDIA RTX A5500

Live eBay prices, cheapest first. The best one right now is $3,033 (open box).

Specs

VRAM
24 GB GDDR6
Bandwidth
768 GB/s
FP32
34.1 TFLOPS
FP16
136 TFLOPS
Power
230 W
Connector
PCIe 4.0
Released
2022
Launch price
$2,499 (est.)
CUDA compute
8.6
Llama 3.1 8B at Q4 (est.)
79–119 tokens/s

Price right now

Live on eBay
Lowest now$3,033
Median ask$3,698
Per GB VRAM$126.37
vs launch price21% over
Live listings22

From the live listings below; shipping included.

Listings

Live on eBay
ListingConditionPriceChecked
Open box$3,033or best offer−18%+$1.65 shipping
Used$3,080or best offer−17%free shipping
Open box$3,247or best offer−12%free shipping
Open box$3,249or best offer−12%free shipping
Open box$3,249or best offer−12%free shipping
Open box$3,249or best offer−12%free shipping
Open box$3,250or best offer−12%free shipping
Used$3,499or best offer−5%free shipping
Open box$3,550or best offerfree shipping
Used$3,600or best offerfree shipping
Used$3,698or best offerfree shipping
Open box$3,699or best offerfree shipping
Open box$3,699or best offerfree shipping
Open box$3,699or best offerfree shipping
Used$3,751or best offerfree shipping
Open box$3,815or best offerfree shipping
Open box$4,129or best offer+$29.90 shipping
Open box$4,296or best offerfree shipping
Open box$4,296or best offerfree shipping
Open box$4,296or best offerfree shipping
New$4,999or best offershipping not listed
Open box$5,423or best offerfree 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 A5500 neededCosts nowSpeed (est.)
Llama 3.1 8B1 card$3,03379–119 tokens/s
Qwen3 14B1 card$3,03343–64 tokens/s
gpt-oss 20B1 card$3,033106–158 tokens/s
Gemma 3 27B1 card$3,03323–35 tokens/s
Qwen3 32B1 card$3,03319–29 tokens/s
Llama 3.3 70B2 cards$6,1139.0–13 tokens/s
gpt-oss 120B4 cards$12,60975–112 tokens/s
Qwen3 235B-A22B7 cards$22,35717–26 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 A5500 neededCosts nowPer question (est.)
Julia-10.144B1 card$3,0336.2–13 ms
Laya0.421B1 card$3,03310–22 ms
Kev-4B4B1 card$3,03325–53 ms
lev4B1 card$3,03374–158 ms
OpenJev27B1 card$3,03388–189 ms
Clef27B1 card$3,03388–189 ms
Perplexity Decider v1.227B1 card$3,03388–189 ms
mammoth-127B1 card$3,03388–189 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 A5500. These open the shop's own search; we don't show their prices here.