NVIDIA GeForce RTX 4080 32 GB
Live eBay prices, cheapest first. The best one right now is $2,550 (new).
Other sizes: 16 GB
Specs
- VRAM
- 32 GB GDDR6X
- Bandwidth
- 717 GB/s
- FP32
- 48.7 TFLOPS
- FP16
- 97 TFLOPS
- Power
- 320 W
- Connector
- PCIe 4.0
- Released
- 2022
- Launch price
- $1,199
- CUDA compute
- 8.9
- Llama 3.1 8B at Q4 (est.)
- 74–111 tokens/s
Price right now
Live on eBayFrom the live listings below; shipping included.
Listings
Live on eBay| Listing | Condition | Price | Checked |
|---|---|---|---|
| New | $2,550or best offer−7%free shipping | ||
| Open box | $2,550or best offer−7%free shipping | ||
| New | $2,550or best offer−7%free shipping | ||
| Open box | $2,550or best offer−7%free shipping | ||
| New | $2,550or best offer−7%free shipping | ||
| Open box | $2,590or best offer−6%free shipping | ||
| Used | $2,699or best offerfree shipping | ||
| Open box | $2,720or best offerfree shipping | ||
| Open box | $2,720or best offerfree shipping | ||
| Open box | $2,720or best offerfree shipping | ||
| Open box | $2,720or best offerfree shipping | ||
| Open box | $2,720or best offerfree shipping | ||
| Open box | $2,720or best offerfree shipping | ||
| New | $2,750or best offerfree shipping | ||
| New | $2,750or best offerfree shipping | ||
| Open box | $2,750free shipping | ||
| Open box | $2,755or best offerfree shipping | ||
| Open box | $2,789or best offerfree shipping | ||
| Used | $2,790or best offerfree shipping | ||
| Open box | $2,790or best offerfree shipping | ||
| Open box | $2,790or best offerfree shipping | ||
| Open box | $2,790or best offerfree shipping | ||
| Open box | $2,790or best offerfree shipping | ||
| Open box | $2,790or best offerfree shipping | ||
| Open box | $2,790or best offerfree shipping | ||
| Open box | $2,790or best offerfree shipping | ||
| Open box | $2,790or best offerfree shipping | ||
| Open box | $2,790or best offerfree shipping | ||
| Open box | $2,805or best offerfree shipping | ||
| Open box | $3,001or best offerfree shipping | ||
| Open box | $3,895or best offerfree 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- #16 of 33 PCIe GPUs with 32 GB or more for the money: $2,493 per GeForce RTX 3090 of performance.
- Software: CUDA 11.8 and newer.
As much VRAM, about as fast, for less
- NVIDIA Tesla V100 PCIe 32 GB: $975.00, 123% of the GeForce RTX 3090, 32 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
Faster, for the least
- NVIDIA Tesla V100 PCIe 12 GB: $261.00, 123% of the GeForce RTX 3090, 12 GB
- 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
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) | GeForce RTX 4080 32 GB needed | Costs now | Speed (est.) |
|---|---|---|---|
| Llama 3.1 8B | 1 card | $2,550 | 74–111 tokens/s |
| Qwen3 14B | 1 card | $2,550 | 40–60 tokens/s |
| gpt-oss 20B | 1 card | $2,550 | 99–148 tokens/s |
| Gemma 3 27B | 1 card | $2,550 | 22–32 tokens/s |
| Qwen3 32B | 1 card | $2,550 | 18–27 tokens/s |
| Llama 3.3 70B | 2 cards | $5,100 | 8.4–13 tokens/s |
| gpt-oss 120B | 3 cards | $7,650 | 70–104 tokens/s |
| Qwen3 235B-A22B | 5 cards | $12,750 | 16–24 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 4080 32 GB needed | Costs now | Per question (est.) |
|---|---|---|---|
| Julia-10.144B | 1 card | $2,550 | 7.5–16 ms |
| Laya0.421B | 1 card | $2,550 | 13–27 ms |
| Kev-4B4B | 1 card | $2,550 | 30–65 ms |
| lev4B | 1 card | $2,550 | 90–194 ms |
| OpenJev27B | 1 card | $2,550 | 108–232 ms |
| Clef27B | 1 card | $2,550 | 108–232 ms |
| Perplexity Decider v1.227B | 1 card | $2,550 | 108–232 ms |
| mammoth-127B | 1 card | $2,550 | 108–232 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 4080 32 GB. These open the shop's own search; we don't show their prices here.






























