NVIDIA GeForce RTX 5080
Live eBay prices, cheapest first. The best one right now is $1,700 (used).
Specs
- VRAM
- 16 GB GDDR7
- Bandwidth
- 960 GB/s
- FP32
- 56.3 TFLOPS
- FP16
- 113 TFLOPS
- Power
- 360 W
- Connector
- PCIe 5.0
- Released
- 2025
- Launch price
- $999.00
- CUDA compute
- 12.0
- Llama 3.1 8B at Q4 (est.)
- 99–148 tokens/s
Price right now
Live on eBayFrom the live listings below; shipping included.
Listings
Live on eBay| Listing | Condition | Price | Checked |
|---|---|---|---|
| Used | $1,700or best offer−29%shipping not listed | ||
| Used | $1,799−25%free shipping | ||
| Used | $1,850−23%shipping not listed | ||
| Open box | $1,850−23%shipping not listed | ||
| Used | $1,890−21%free shipping | ||
| Used | $1,900or best offer−21%free shipping | ||
| Used | $1,900−21%free shipping | ||
| Used | $1,900−21%free shipping | ||
| Refurbished | $1,940−19%free shipping | ||
| Used | $1,949−19%shipping not listed | ||
| Refurbished | $1,950−19%free shipping | ||
| New | $1,950−19%shipping not listed | ||
| New | $1,950or best offer−19%shipping not listed | ||
| Refurbished | $1,970−18%free shipping | ||
| Used | $1,970−18%+$19.99 shipping | ||
| Refurbished | $1,999−17%free shipping | ||
| New | $1,999−17%free shipping | ||
| New | $1,999−17%free shipping | ||
| Open box | $1,999−17%shipping not listed | ||
| New | $2,000or best offer−17%free shipping | ||
| Used | $2,000or best offer−17%free shipping | ||
| New | $2,000−17%free shipping | ||
| Open box | $2,000or best offer−17%free shipping | ||
| Used | $2,000or best offer−17%free shipping | ||
| New | $2,000or best offer−17%shipping not listed | ||
| Used | $2,000or best offer−17%shipping not listed | ||
| Used | $2,000−17%shipping not listed | ||
| Used | $2,000or best offer−17%free shipping | ||
| Used | $2,000−17%shipping not listed | ||
| Used | $2,000or best offer−17%shipping not listed | ||
| New | $2,003or best offer−17%+$36.38 shipping | ||
| Used | $2,019−16%+$19.99 shipping | ||
| Refurbished | $2,030−15%free shipping | ||
| Used | $2,030−15%+$29.99 shipping | ||
| New | $2,040−15%free shipping | ||
| Open box | $2,049−15%shipping not listed | ||
| New | $2,050−15%+$49.99 shipping | ||
| New | $2,050or best offer−15%free shipping | ||
| Open box | $2,050−15%free shipping | ||
| Used | $2,050−15%free shipping | ||
| Used | $2,050−15%free shipping | ||
| Used | $2,050or best offer−15%shipping not listed | ||
| New | $2,058or best offer−14%+$12.52 shipping | ||
| Used | $2,069−14%+$19.99 shipping | ||
| New | $2,070−14%free shipping | ||
| Refurbished | $2,070−14%free shipping | ||
| New | $2,099−13%shipping not listed | ||
| New | $2,100−13%free shipping | ||
| New | $2,100or best offer−13%shipping not listed | ||
| New | $2,100−13%free shipping | ||
| Open box | $2,100or best offer−12%shipping not listed | ||
| New | $2,112−12%+$12.95 shipping | ||
| Used | $2,120−12%+$19.99 shipping | ||
| Open box | $2,140or best offer−11%+$40.00 shipping | ||
| New | $2,150or best offer−10%shipping not listed | ||
| New | $2,150or best offer−10%shipping not listed | ||
| New | $2,150or best offer−10%free shipping | ||
| Open box | $2,150or best offer−10%free shipping | ||
| New | $2,150−10%free shipping | ||
| New | $2,199−8%free shipping |
Showing the 60 cheapest of 190 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- #40 of 83 PCIe GPUs with 16 GB or more for the money: $1,331 per GeForce RTX 3090 of performance.
- Software: CUDA 12.8 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
- AMD Radeon RX 9070: $800.00, 118% of the GeForce RTX 3090, 16 GB
- AMD Radeon RX 9070 XT: $890.00, 137% of the GeForce RTX 3090, 16 GB
Faster, for the least
- NVIDIA Tesla V100S PCIe: $1,099, 149% of the GeForce RTX 3090, 32 GB
- AMD Instinct MI100: $1,240, 185% of the GeForce RTX 3090, 32 GB
- NVIDIA GeForce RTX 4090: $2,094, 158% of the GeForce RTX 3090, 24 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 A40, vs Radeon RX 7900 XTX, vs Tesla V100 SXM2 16 GB.
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 5080 needed | Costs now | Speed (est.) |
|---|---|---|---|
| Llama 3.1 8B | 1 card | $1,700 | 99–148 tokens/s |
| Qwen3 14B | 1 card | $1,700 | 53–80 tokens/s |
| gpt-oss 20B | 1 card | $1,700 | 132–198 tokens/s |
| Gemma 3 27B | 2 cards | $3,499 | 29–43 tokens/s |
| Qwen3 32B | 2 cards | $3,499 | 24–36 tokens/s |
| Llama 3.3 70B | 4 cards | $7,199 | 11–17 tokens/s |
| gpt-oss 120B | 5 cards | $9,089 | 93–140 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 5080 needed | Costs now | Per question (est.) |
|---|---|---|---|
| Julia-10.144B | 1 card | $1,700 | 6.0–13 ms |
| Laya0.421B | 1 card | $1,700 | 10–22 ms |
| Kev-4B4B | 1 card | $1,700 | 24–52 ms |
| lev4B | 1 card | $1,700 | 72–155 ms |
| OpenJev27B | 2 cards | $3,499 | 87–185 ms |
| Clef27B | 2 cards | $3,499 | 87–185 ms |
| Perplexity Decider v1.227B | 2 cards | $3,499 | 87–185 ms |
| mammoth-127B | 2 cards | $3,499 | 87–185 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 5080. These open the shop's own search; we don't show their prices here.



























































