NVIDIA RTX 2000 Ada
Live eBay prices, cheapest first. The best one right now is $590.00 (used).
Other sizes: 8 GB
Specs
- VRAM
- 16 GB GDDR6
- Bandwidth
- 224 GB/s
- FP32
- 12 TFLOPS
- FP16
- 48 TFLOPS
- Power
- 70 W
- Connector
- PCIe 4.0
- Released
- 2024
- Launch price
- $625.00
- CUDA compute
- 8.9
- Llama 3.1 8B at Q4 (est.)
- 23–35 tokens/s
Price right now
Live on eBayFrom the live listings below; shipping included.
Listings
Live on eBay| Listing | Condition | Price | Checked |
|---|---|---|---|
| Used | $590.00or best offer−38%shipping not listed | ||
| Used | $706.97−26%free shipping | ||
| Open box | $728.97−24%free shipping | ||
| Used | $729.00or best offer−24%free shipping | ||
| Used | $739.00or best offer−23%free shipping | ||
| Used | $759.98or best offer−21%+$9.99 shipping | ||
| New | $791.00−18%free shipping | ||
| New | $798.00−17%free shipping | ||
| Used | $848.00or best offer−12%free shipping | ||
| Used | $849.00or best offer−11%free shipping | ||
| Used | $849.99or best offer−11%free shipping | ||
| Used | $854.40or best offer−11%free shipping | ||
| Open box | $855.00or best offer−11%free shipping | ||
| Open box | $859.00or best offer−10%free shipping | ||
| Open box | $859.00or best offer−10%free shipping | ||
| Open box | $859.00or best offer−10%free shipping | ||
| Open box | $859.00or best offer−10%free shipping | ||
| New | $859.77−10%free shipping | ||
| Open box | $860.00or best offer−10%free shipping | ||
| New | $879.52−8%free shipping | ||
| New | $882.44−8%free shipping | ||
| New | $893.18or best offer−7%shipping not listed | ||
| Open box | $895.00−7%free shipping | ||
| Open box | $899.00or best offer−6%free shipping | ||
| New | $900.00or best offer−6%shipping not listed | ||
| Open box | $913.81or best offerfree shipping | ||
| Open box | $918.98or best offerfree shipping | ||
| Open box | $919.00or best offerfree shipping | ||
| Open box | $920.00or best offerfree shipping | ||
| Open box | $924.81free shipping | ||
| New | $937.99or best offerfree shipping | ||
| New | $939.00or best offerfree shipping | ||
| New | $950.00or best offerfree shipping | ||
| Open box | $950.00or best offerfree shipping | ||
| Open box | $959.00or best offerfree shipping | ||
| Open box | $959.00free shipping | ||
| Open box | $959.00or best offerfree shipping | ||
| Open box | $959.00or best offerfree shipping | ||
| Used | $959.18or best offer+$66.00 shipping | ||
| Used | $959.18or best offer+$66.00 shipping | ||
| Open box | $994.90or best offer+$29.90 shipping | ||
| New | $999.00shipping not listed | ||
| Open box | $1,000or best offerfree shipping | ||
| Open box | $1,008or best offer+$7.99 shipping | ||
| New | $1,067free shipping | ||
| New | $1,081+$52.00 shipping | ||
| New | $1,087or best offer+$77.16 shipping | ||
| New | $1,099free shipping | ||
| New | $1,151free shipping | ||
| New | $1,163free shipping | ||
| Open box | $1,167or best offerfree shipping | ||
| New | $1,220or best offershipping not listed | ||
| Used | $1,225+$58.00 shipping | ||
| New | $1,228free shipping | ||
| New | $1,254free shipping | ||
| New | $1,292free shipping | ||
| Open box | $1,300+$275.58 shipping | ||
| New | $1,402+$46.00 shipping | ||
| New | $1,435+$26.00 shipping | ||
| New | $1,442+$52.00 shipping |
Showing the 60 cheapest of 70 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- #42 of 83 PCIe GPUs with 16 GB or more for the money: $1,467 per GeForce RTX 3090 of performance.
- Software: CUDA 11.8 and newer.
As much VRAM, about as fast, for less
- NVIDIA Tesla P100 PCIe 16 GB: $170.00, 45% of the GeForce RTX 3090, 16 GB
- AMD Radeon VII: $249.00, 65% of the GeForce RTX 3090, 16 GB
- AMD Instinct MI50 16 GB: $266.00, 64% of the GeForce RTX 3090, 16 GB
Faster, for the least
- NVIDIA GeForce RTX 2070 Super: $169.99, 49% of the GeForce RTX 3090, 8 GB
- NVIDIA Quadro RTX 4000: $175.00, 60% of the GeForce RTX 3090, 8 GB
- NVIDIA GeForce RTX 2080: $175.00, 52% of the GeForce RTX 3090, 8 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 4060 Ti 8 GB, vs Radeon RX 6700 XT, vs Radeon RX 7600.
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) | RTX 2000 Ada needed | Costs now | Speed (est.) |
|---|---|---|---|
| Llama 3.1 8B | 1 card | $590.00 | 23–35 tokens/s |
| Qwen3 14B | 1 card | $590.00 | 12–19 tokens/s |
| gpt-oss 20B | 1 card | $590.00 | 31–46 tokens/s |
| Gemma 3 27B | 2 cards | $1,297 | 6.7–10 tokens/s |
| Qwen3 32B | 2 cards | $1,297 | 5.6–8.4 tokens/s |
| Llama 3.3 70B | 4 cards | $2,755 | 2.6–3.9 tokens/s |
| gpt-oss 120B | 5 cards | $3,494 | 22–33 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) | RTX 2000 Ada needed | Costs now | Per question (est.) |
|---|---|---|---|
| Julia-10.144B | 1 card | $590.00 | 19–41 ms |
| Laya0.421B | 1 card | $590.00 | 32–68 ms |
| Kev-4B4B | 1 card | $590.00 | 77–164 ms |
| lev4B | 1 card | $590.00 | 230–493 ms |
| OpenJev27B | 2 cards | $1,297 | 275–589 ms |
| Clef27B | 2 cards | $1,297 | 275–589 ms |
| Perplexity Decider v1.227B | 2 cards | $1,297 | 275–589 ms |
| mammoth-127B | 2 cards | $1,297 | 275–589 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 RTX 2000 Ada. These open the shop's own search; we don't show their prices here.
























































