PerGB

NVIDIA GeForce RTX 4080

Live eBay prices, cheapest first. The best one right now is $1,200 (used).

Other sizes: 32 GB

Specs

VRAM
16 GB GDDR6X
Bandwidth
717 GB/s
FP32
48.7 TFLOPS
FP16
97 TFLOPS
Power
320 W
Connector
PCIe 4.0
Released
2022
Launch price
$1,199
CUDA compute
8.9
Llama 3.1 8B at Q4 (est.)
74–111 tokens/s

Price right now

Live on eBay
Lowest now$1,200
Median ask$1,800
Per GB VRAM$75.00
vs launch priceat launch price
Live listings86

From the live listings below; shipping included.

Listings

Live on eBay
ListingConditionPriceChecked
Used$1,200−33%free shipping
Used$1,246or best offer−31%shipping not listed
Used$1,250or best offer−31%Check carefullyshipping not listed
Used$1,250or best offer−31%Check carefullyshipping not listed
Open box$1,258or best offer−30%Check carefully+$8.23 shipping
Used$1,270−29%free shipping
Used$1,299or best offer−28%shipping not listed
Refurbished$1,300−28%free shipping
Used$1,300or best offer−28%free shipping
Used$1,300or best offer−28%shipping not listed
Used$1,300or best offer−28%shipping not listed
Open box$1,300or best offer−28%shipping not listed
New$1,306or best offer−27%+$6.00 shipping
Used$1,309or best offer−27%+$10.00 shipping
Used$1,320or best offer−27%shipping not listed
Used$1,320−27%free shipping
Used$1,350or best offer−25%shipping not listed
Used$1,350−25%shipping not listed
Refurbished$1,360−24%free shipping
Refurbished$1,360−24%free shipping
Used$1,400or best offer−22%free shipping
New$1,407−22%+$50.00 shipping
Used$1,420−21%+$20.00 shipping
Refurbished$1,500−17%free shipping
Used$1,500−17%free shipping
Used$1,570or best offer−13%+$19.99 shipping
New$1,589or best offer−12%free shipping
New$1,600−11%free shipping
New$1,640or best offer−9%free shipping
Used$1,699or best offer−6%shipping not listed
Used$1,752shipping not listed
Used$1,799or best offershipping not listed
Refurbished$1,800free shipping
Refurbished$1,800free shipping
Refurbished$1,800free shipping
Refurbished$1,800free shipping
Refurbished$1,800free shipping
Refurbished$1,800free shipping
Refurbished$1,800free shipping
Refurbished$1,800free shipping
Refurbished$1,800free shipping
Refurbished$1,800free shipping
Refurbished$1,800free shipping
Open box$1,800or best offershipping not listed
Open box$1,818or best offerfree shipping
Used$1,862+$11.50 shipping
New$1,873or best offerfree shipping
New$1,873or best offerfree shipping
New$1,890or best offerfree shipping
New$1,890or best offerfree shipping
New$1,890or best offerfree shipping
Open box$1,950or best offerfree shipping
New$1,960or best offerfree shipping
New$1,989or best offerfree shipping
New$2,029or best offer+$29.90 shipping
New$2,050or best offerfree shipping
Open box$2,050or best offerfree shipping
New$2,050or best offerfree shipping
New$2,050or best offerfree shipping
Open box$2,050or best offerfree shipping

Showing the 60 cheapest of 86 listings.

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

Compare: vs GeForce RTX 3080 Ti, vs GeForce RTX 3090, vs GeForce RTX 4080 Super.

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)GeForce RTX 4080 neededCosts nowSpeed (est.)
Llama 3.1 8B1 card$1,20074–111 tokens/s
Qwen3 14B1 card$1,20040–60 tokens/s
gpt-oss 20B1 card$1,20099–148 tokens/s
Gemma 3 27B2 cards$2,44522–32 tokens/s
Qwen3 32B2 cards$2,44518–27 tokens/s
Llama 3.3 70B4 cards$4,9458.4–13 tokens/s
gpt-oss 120B5 cards$6,20470–104 tokens/s
Qwen3 235B-A22Bmore than 8——
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)GeForce RTX 4080 neededCosts nowPer question (est.)
Julia-10.144B1 card$1,2007.5–16 ms
Laya0.421B1 card$1,20013–27 ms
Kev-4B4B1 card$1,20030–65 ms
lev4B1 card$1,20090–194 ms
OpenJev27B2 cards$2,445108–232 ms
Clef27B2 cards$2,445108–232 ms
Perplexity Decider v1.227B2 cards$2,445108–232 ms
mammoth-127B2 cards$2,445108–232 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 GeForce RTX 4080. These open the shop's own search; we don't show their prices here.