NVIDIA GeForce RTX 3090 Ti
Live eBay prices, cheapest first. The best one right now is $1,750 (used).
Specs
- VRAM
- 24 GB GDDR6X
- Bandwidth
- 1,008 GB/s
- FP32
- 40 TFLOPS
- FP16
- 80 TFLOPS
- Power
- 450 W
- Connector
- PCIe 4.0
- Released
- 2022
- Launch price
- $1,999
- CUDA compute
- 8.6
- Llama 3.1 8B at Q4 (est.)
- 104–156 tokens/s
Price right now
Live on eBayFrom the live listings below; shipping included.
Listings
Live on eBay| Listing | Condition | Price | Checked |
|---|---|---|---|
| Used | $1,750or best offer−27%shipping not listed | ||
| Used | $1,800−25%shipping not listed | ||
| Refurbished | $1,899−21%free shipping | ||
| Used | $1,900or best offer−21%shipping not listed | ||
| Used | $1,970or best offer−18%free shipping | ||
| Used | $1,971or best offer−18%+$20.91 shipping | ||
| Used | $1,999or best offer−17%shipping not listed | ||
| Used | $2,040or best offer−15%+$40.00 shipping | ||
| Refurbished | $2,050−15%free shipping | ||
| Used | $2,050or best offer−15%shipping not listed | ||
| Used | $2,100or best offer−12%shipping not listed | ||
| Used | $2,100or best offer−12%free shipping | ||
| Refurbished | $2,180−9%free shipping | ||
| Refurbished | $2,180−9%free shipping | ||
| Refurbished | $2,190−9%free shipping | ||
| Used | $2,230−7%free shipping | ||
| Used | $2,247−6%free shipping | ||
| Used | $2,248or best offer−6%free shipping | ||
| New | $2,373or best offer+$23.32 shipping | ||
| New | $2,399or best offerfree shipping | ||
| Used | $2,399free shipping | ||
| New | $2,399or best offerfree shipping | ||
| New | $2,399or best offerfree shipping | ||
| Refurbished | $2,400free shipping | ||
| Used | $2,475or best offerfree shipping | ||
| Open box | $2,501or best offerfree shipping | ||
| New | $2,534or best offerfree shipping | ||
| Used | $2,650or best offerfree shipping | ||
| Used | $2,650or best offerfree shipping | ||
| Used | $2,650or best offerfree shipping | ||
| New | $2,650or best offerfree shipping | ||
| Used | $2,650or best offerfree shipping | ||
| Used | $2,650or best offerfree shipping | ||
| New | $2,650or best offerfree shipping | ||
| Used | $2,650or best offerfree shipping | ||
| Used | $2,699free shipping | ||
| New | $2,837or best offerfree shipping | ||
| New | $2,837or best offerfree shipping | ||
| Used | $2,899free shipping | ||
| Used | $2,899free shipping | ||
| Used | $2,899free shipping | ||
| New | $2,919or best offer+$38.88 shipping | ||
| Used | $2,999shipping not listed |
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- #14 of 49 PCIe GPUs with 24 GB or more for the money: $1,589 per GeForce RTX 3090 of performance.
- Software: CUDA 11.1 and newer.
As much VRAM, about as fast, for less
- AMD Radeon RX 7900 XTX: $900.00, 133% of the GeForce RTX 3090, 24 GB
- NVIDIA Titan RTX: $910.00, 115% of the GeForce RTX 3090, 24 GB
- NVIDIA Tesla V100 PCIe 32 GB: $975.00, 123% of the GeForce RTX 3090, 32 GB
Faster, for the least
- AMD Radeon RX 9070 XT: $890.00, 137% of the GeForce RTX 3090, 16 GB
- 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
More VRAM, for not much more
- AMD Instinct MI50 32 GB: $633.68, 64% of the GeForce RTX 3090, 32 GB
- AMD Radeon Pro W6800: $879.99, 52% of the GeForce RTX 3090, 32 GB
- NVIDIA Tesla V100 PCIe 32 GB: $975.00, 123% of the GeForce RTX 3090, 32 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 3090 Ti needed | Costs now | Speed (est.) |
|---|---|---|---|
| Llama 3.1 8B | 1 card | $1,750 | 104–156 tokens/s |
| Qwen3 14B | 1 card | $1,750 | 56–84 tokens/s |
| gpt-oss 20B | 1 card | $1,750 | 139–208 tokens/s |
| Gemma 3 27B | 1 card | $1,750 | 30–46 tokens/s |
| Qwen3 32B | 1 card | $1,750 | 25–38 tokens/s |
| Llama 3.3 70B | 2 cards | $3,550 | 12–18 tokens/s |
| gpt-oss 120B | 4 cards | $7,349 | 98–147 tokens/s |
| Qwen3 235B-A22B | 7 cards | $13,289 | 23–34 tokens/s |
| 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 3090 Ti needed | Costs now | Per question (est.) |
|---|---|---|---|
| Julia-10.144B | 1 card | $1,750 | 7.0–15 ms |
| Laya0.421B | 1 card | $1,750 | 12–25 ms |
| Kev-4B4B | 1 card | $1,750 | 28–60 ms |
| lev4B | 1 card | $1,750 | 84–180 ms |
| OpenJev27B | 1 card | $1,750 | 100–215 ms |
| Clef27B | 1 card | $1,750 | 100–215 ms |
| Perplexity Decider v1.227B | 1 card | $1,750 | 100–215 ms |
| mammoth-127B | 1 card | $1,750 | 100–215 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 3090 Ti. These open the shop's own search; we don't show their prices here.








































