NVIDIA RTX PRO 2000 Blackwell 8 GB
Live eBay prices, cheapest first. The best one right now is $280.56 (open box).
Other sizes: 16 GB
Specs
- VRAM
- 8 GB GDDR7
- Bandwidth
- 288 GB/s
- FP32
- 17 TFLOPS
- FP16
- 70 TFLOPS
- Power
- 70 W
- Connector
- PCIe 5.0
- Released
- 2025
- Launch price
- $699.00 (est.)
- CUDA compute
- 12.0
- Llama 3.1 8B at Q4 (est.)
- 30–45 tokens/s
Price right now
Live on eBayFrom the live listings below; shipping included.
Listings
Live on eBay| Listing | Condition | Price | Checked |
|---|---|---|---|
| Open box | $280.56free 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- Software: CUDA 12.8 and newer.
As much VRAM, about as fast, for less
- 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
- NVIDIA GeForce RTX 3070: $199.99, 53% of the GeForce RTX 3090, 8 GB
Faster, for the least
- AMD Radeon VII: $249.00, 65% of the GeForce RTX 3090, 16 GB
- Intel Arc A770 8 GB: $259.99, 103% of the GeForce RTX 3090, 8 GB
- NVIDIA Tesla V100 PCIe 12 GB: $261.00, 123% of the GeForce RTX 3090, 12 GB
More VRAM, for not much more
- NVIDIA Tesla P100 PCIe 12 GB: $128.00, 39% of the GeForce RTX 3090, 12 GB
- 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
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 PRO 2000 Blackwell 8 GB needed | Costs now | Speed (est.) |
|---|---|---|---|
| Llama 3.1 8B | 1 card | $280.56 | 30–45 tokens/s |
| Qwen3 14B | 2 cards | not enough listings | 16–24 tokens/s |
| gpt-oss 20B | 2 cards | not enough listings | 40–59 tokens/s |
| Gemma 3 27B | 4 cards | not enough listings | 8.7–13 tokens/s |
| Qwen3 32B | 4 cards | not enough listings | 7.2–11 tokens/s |
| Llama 3.3 70B | 7 cards | not enough listings | 3.4–5.0 tokens/s |
| gpt-oss 120B | more than 8 | — | — |
| 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 PRO 2000 Blackwell 8 GB needed | Costs now | Per question (est.) |
|---|---|---|---|
| Julia-10.144B | 1 card | $280.56 | 14–30 ms |
| Laya0.421B | 1 card | $280.56 | 23–50 ms |
| Kev-4B4B | 1 card | $280.56 | 56–120 ms |
| lev4B | 1 card | $280.56 | 168–360 ms |
| OpenJev27B | 3 cards | not enough listings | 201–430 ms |
| Clef27B | 3 cards | not enough listings | 201–430 ms |
| Perplexity Decider v1.227B | 3 cards | not enough listings | 201–430 ms |
| mammoth-127B | 3 cards | not enough listings | 201–430 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 PRO 2000 Blackwell 8 GB. These open the shop's own search; we don't show their prices here.
