NVIDIA GeForce RTX 4080 Super
Live eBay prices, cheapest first. The best one right now is $1,200 (used).
Other sizes: 32 GB
Specs
- VRAM
- 16 GB GDDR6X
- Bandwidth
- 736 GB/s
- FP32
- 52.2 TFLOPS
- FP16
- 104 TFLOPS
- Power
- 320 W
- Connector
- PCIe 4.0
- Released
- 2024
- Launch price
- $999.00
- CUDA compute
- 8.9
- Llama 3.1 8B at Q4 (est.)
- 76–114 tokens/s
Price right now
Live on eBayFrom the live listings below; shipping included.
Listings
Live on eBay| Listing | Condition | Price | Checked |
|---|---|---|---|
| Used | $1,200or best offer−38%shipping not listed | ||
| Used | $1,224or best offer−37%+$25.00 shipping | ||
| Used | $1,300or best offer−33%free shipping | ||
| New | $1,300or best offer−33%shipping not listed | ||
| Used | $1,300or best offer−33%Check carefullyshipping not listed | ||
| Used | $1,350−31%shipping not listed | ||
| Used | $1,350or best offer−31%Check carefullyshipping not listed | ||
| Used | $1,390−29%+$9.99 shipping | ||
| Used | $1,400or best offer−28%free shipping | ||
| Used | $1,400−28%free shipping | ||
| Open box | $1,400−28%shipping not listed | ||
| Used | $1,400or best offer−28%free shipping | ||
| Used | $1,408or best offer−28%+$7.94 shipping | ||
| Used | $1,480−24%free shipping | ||
| Used | $1,500−23%shipping not listed | ||
| Open box | $1,507or best offer−23%free shipping | ||
| Used | $1,530or best offer−21%free shipping | ||
| New | $1,540−21%+$60.00 shipping | ||
| Used | $1,550−20%free shipping | ||
| Used | $1,550or best offer−20%shipping not listed | ||
| Open box | $1,555−20%shipping not listed | ||
| Used | $1,570−19%+$20.00 shipping | ||
| New | $1,577or best offer−19%free shipping | ||
| Used | $1,620−17%+$20.00 shipping | ||
| Used | $1,647or best offer−15%free shipping | ||
| Used | $1,648or best offer−15%free shipping | ||
| Used | $1,649or best offer−15%free shipping | ||
| Used | $1,650−15%free shipping | ||
| Used | $1,670−14%+$20.00 shipping | ||
| New | $1,696or best offer−13%free shipping | ||
| New | $1,699or best offer−13%free shipping | ||
| Open box | $1,749or best offer−10%free shipping | ||
| New | $1,750−10%free shipping | ||
| Used | $1,800or best offer−7%shipping not listed | ||
| Used | $1,800or best offer−7%shipping not listed | ||
| Used | $1,819or best offer−6%free shipping | ||
| Used | $1,822−6%+$175.19 shipping | ||
| Used | $1,854free shipping | ||
| Used | $1,899or best offerfree shipping | ||
| Used | $1,899or best offerfree shipping | ||
| Used | $1,899or best offerfree shipping | ||
| New | $1,900or best offershipping not listed | ||
| Used | $1,914+$14.29 shipping | ||
| Used | $1,945or best offerfree shipping | ||
| Used | $1,945or best offerfree shipping | ||
| Used | $1,945or best offerfree shipping | ||
| Refurbished | $2,000free shipping | ||
| Refurbished | $2,000free shipping | ||
| Refurbished | $2,000free shipping | ||
| Refurbished | $2,000free shipping | ||
| Refurbished | $2,000free shipping | ||
| Refurbished | $2,000free shipping | ||
| Used | $2,000or best offershipping not listed | ||
| Used | $2,050free shipping | ||
| Used | $2,050free shipping | ||
| Used | $2,050free shipping | ||
| Used | $2,050free shipping | ||
| Used | $2,200free shipping | ||
| New | $2,267or best offer+$67.46 shipping | ||
| Open box | $2,314or best offerfree shipping |
Showing the 60 cheapest of 87 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- #34 of 83 PCIe GPUs with 16 GB or more for the money: $1,118 per GeForce RTX 3090 of performance.
- Software: CUDA 11.8 and newer.
As much VRAM, about as fast, for less
- NVIDIA Tesla V100 PCIe 16 GB: $325.00, 123% of the GeForce RTX 3090, 16 GB
- Intel Arc A770 16 GB: $431.00, 108% of the GeForce RTX 3090, 16 GB
- AMD Radeon RX 9070: $800.00, 118% of the GeForce RTX 3090, 16 GB
Faster, for the least
- AMD Radeon RX 9070 XT: $890.00, 137% of the GeForce RTX 3090, 16 GB
- AMD Radeon RX 7900 XTX: $900.00, 133% of the GeForce RTX 3090, 24 GB
- NVIDIA Tesla V100S PCIe: $1,099, 149% of the GeForce RTX 3090, 32 GB
More VRAM, for not much more
- NVIDIA Tesla P40: $270.00, 35% of the GeForce RTX 3090, 24 GB
- NVIDIA GeForce RTX 3080 20 GB: $597.36, 91% of the GeForce RTX 3090, 20 GB
- AMD Instinct MI50 32 GB: $633.68, 64% of the GeForce RTX 3090, 32 GB
Compare: vs RTX A5000, vs GeForce RTX 4080, vs GeForce RTX 5070 Ti.
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 Super needed | Costs now | Speed (est.) |
|---|---|---|---|
| Llama 3.1 8B | 1 card | $1,200 | 76–114 tokens/s |
| Qwen3 14B | 1 card | $1,200 | 41–62 tokens/s |
| gpt-oss 20B | 1 card | $1,200 | 101–152 tokens/s |
| Gemma 3 27B | 2 cards | $2,424 | 22–33 tokens/s |
| Qwen3 32B | 2 cards | $2,424 | 19–28 tokens/s |
| Llama 3.3 70B | 4 cards | $5,024 | 8.6–13 tokens/s |
| gpt-oss 120B | 5 cards | $6,324 | 71–107 tokens/s |
| Qwen3 235B-A22B | more than 8 | — | — |
| DeepSeek R1 / V3 671B | more 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 Super needed | Costs now | Per question (est.) |
|---|---|---|---|
| Julia-10.144B | 1 card | $1,200 | 7.2–15 ms |
| Laya0.421B | 1 card | $1,200 | 12–26 ms |
| Kev-4B4B | 1 card | $1,200 | 29–62 ms |
| lev4B | 1 card | $1,200 | 86–185 ms |
| OpenJev27B | 2 cards | $2,424 | 103–221 ms |
| Clef27B | 2 cards | $2,424 | 103–221 ms |
| Perplexity Decider v1.227B | 2 cards | $2,424 | 103–221 ms |
| mammoth-127B | 2 cards | $2,424 | 103–221 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 Super. These open the shop's own search; we don't show their prices here.


























































