NVIDIA RTX 5000 Ada
Live eBay prices, cheapest first. The best one right now is $5,499 (new).
Specs
- VRAM
- 32 GB GDDR6
- Bandwidth
- 576 GB/s
- FP32
- 65.3 TFLOPS
- FP16
- 261 TFLOPS
- Power
- 250 W
- Connector
- PCIe 4.0
- Released
- 2023
- Launch price
- $4,000
- CUDA compute
- 8.9
- Llama 3.1 8B at Q4 (est.)
- 59–89 tokens/s
Price right now
Live on eBayFrom the live listings below; shipping included.
Listings
Live on eBay| Listing | Condition | Price | Checked |
|---|---|---|---|
| New | $5,499−22%+$52.00 shipping | ||
| New | $5,678−19%+$52.00 shipping | ||
| New | $5,721−19%+$220.35 shipping | ||
| Open box | $6,314or best offer−10%free shipping | ||
| New | $6,549−7%free shipping | ||
| New | $6,599or best offer−6%free shipping | ||
| New | $6,850or best offerfree shipping | ||
| New | $6,895+$57.00 shipping | ||
| New | $7,004+$26.00 shipping | ||
| Open box | $7,038or best offerfree shipping | ||
| Open box | $7,185or best offerfree shipping | ||
| Open box | $7,185or best offerfree shipping | ||
| Open box | $7,185or best offerfree shipping | ||
| Open box | $7,185or best offerfree shipping | ||
| Open box | $7,185or best offerfree shipping | ||
| Open box | $7,185or best offerfree shipping | ||
| Open box | $7,185or best offerfree shipping | ||
| Open box | $7,550or best offer+$50.00 shipping | ||
| New | $7,640+$49.90 shipping |
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- #28 of 33 PCIe GPUs with 32 GB or more for the money: $3,656 per GeForce RTX 3090 of performance.
- Software: CUDA 11.8 and newer.
As much VRAM, about as fast, for less
- 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
- AMD Radeon AI PRO R9700: $1,999, 136% of the GeForce RTX 3090, 32 GB
Faster, for the least
- AMD Instinct MI210: $3,799, 211% of the GeForce RTX 3090, 64 GB
- NVIDIA GeForce RTX 5090: $5,000, 237% of the GeForce RTX 3090, 32 GB
- NVIDIA A100 PCIe 40 GB: $5,588, 270% of the GeForce RTX 3090, 40 GB
More VRAM, for not much more
- NVIDIA Quadro RTX 8000: $2,000, 115% of the GeForce RTX 3090, 48 GB
- Intel Arc Pro B60 48 GB: $2,049, 82% of the GeForce RTX 3090, 48 GB
- NVIDIA A16: $2,200, 93% of the GeForce RTX 3090, 64 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) | RTX 5000 Ada needed | Costs now | Speed (est.) |
|---|---|---|---|
| Llama 3.1 8B | 1 card | $5,499 | 59–89 tokens/s |
| Qwen3 14B | 1 card | $5,499 | 32–48 tokens/s |
| gpt-oss 20B | 1 card | $5,499 | 79–119 tokens/s |
| Gemma 3 27B | 1 card | $5,499 | 17–26 tokens/s |
| Qwen3 32B | 1 card | $5,499 | 14–22 tokens/s |
| Llama 3.3 70B | 2 cards | $11,177 | 6.7–10 tokens/s |
| gpt-oss 120B | 3 cards | $16,898 | 56–84 tokens/s |
| Qwen3 235B-A22B | 5 cards | $29,761 | 13–19 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) | RTX 5000 Ada needed | Costs now | Per question (est.) |
|---|---|---|---|
| Julia-10.144B | 1 card | $5,499 | 5.1–11 ms |
| Laya0.421B | 1 card | $5,499 | 8.5–18 ms |
| Kev-4B4B | 1 card | $5,499 | 21–44 ms |
| lev4B | 1 card | $5,499 | 62–132 ms |
| OpenJev27B | 1 card | $5,499 | 73–157 ms |
| Clef27B | 1 card | $5,499 | 73–157 ms |
| Perplexity Decider v1.227B | 1 card | $5,499 | 73–157 ms |
| mammoth-127B | 1 card | $5,499 | 73–157 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 5000 Ada. These open the shop's own search; we don't show their prices here.


















