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 eBayFrom the live listings below; shipping included.
Listings
Live on eBay| Listing | Condition | Price | Checked |
|---|---|---|---|
| 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- #35 of 83 PCIe GPUs with 16 GB or more for the money: $1,173 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
- NVIDIA Tesla V100 PCIe 12 GB: $261.00, 123% of the GeForce RTX 3090, 12 GB
- AMD Radeon RX 9070 12 GB: $847.00, 118% of the GeForce RTX 3090, 12 GB
- AMD Radeon RX 9070 XT: $890.00, 137% of the GeForce RTX 3090, 16 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 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 needed | Costs now | Speed (est.) |
|---|---|---|---|
| Llama 3.1 8B | 1 card | $1,200 | 74–111 tokens/s |
| Qwen3 14B | 1 card | $1,200 | 40–60 tokens/s |
| gpt-oss 20B | 1 card | $1,200 | 99–148 tokens/s |
| Gemma 3 27B | 2 cards | $2,445 | 22–32 tokens/s |
| Qwen3 32B | 2 cards | $2,445 | 18–27 tokens/s |
| Llama 3.3 70B | 4 cards | $4,945 | 8.4–13 tokens/s |
| gpt-oss 120B | 5 cards | $6,204 | 70–104 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 needed | Costs now | Per question (est.) |
|---|---|---|---|
| Julia-10.144B | 1 card | $1,200 | 7.5–16 ms |
| Laya0.421B | 1 card | $1,200 | 13–27 ms |
| Kev-4B4B | 1 card | $1,200 | 30–65 ms |
| lev4B | 1 card | $1,200 | 90–194 ms |
| OpenJev27B | 2 cards | $2,445 | 108–232 ms |
| Clef27B | 2 cards | $2,445 | 108–232 ms |
| Perplexity Decider v1.227B | 2 cards | $2,445 | 108–232 ms |
| mammoth-127B | 2 cards | $2,445 | 108–232 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.



























































