PerGB

NVIDIA GeForce RTX 2060 8 GB

Live eBay prices, cheapest first. The best one right now is $200.00 (used).

Other sizes: 6 GB, 12 GB

Specs

VRAM
8 GB GDDR6
Bandwidth
336 GB/s
FP32
6.5 TFLOPS
FP16
26 TFLOPS
Power
160 W
Connector
PCIe 3.0
Released
2019
CUDA compute
7.5
Llama 3.1 8B at Q4 (est.)
35–52 tokens/s

Price right now

Live on eBay
Lowest now$200.00
Median ask$267.50
Per GB VRAM$25.00
vs launch price—
Live listings10

From the live listings below; shipping included.

Listings

Live on eBay
ListingConditionPriceChecked
Used$200.00or best offer−25%shipping not listed
Used$205.68or best offer−23%+$5.68 shipping
Used$206.59−23%free shipping
Used$224.97or best offer−16%shipping not listed
Used$265.00or best offer+$25.00 shipping
Used$270.00or best offershipping not listed
New$286.27or best offerfree shipping
Used$350.00or best offershipping not listed
New$389.99free shipping
New$448.99free 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

As much VRAM, about as fast, for less

Faster, for the least

More VRAM, for not much more

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 2060 8 GB neededCosts nowSpeed (est.)
Llama 3.1 8B1 card$200.0035–52 tokens/s
Qwen3 14B2 cards$405.6819–28 tokens/s
gpt-oss 20B2 cards$405.6846–69 tokens/s
Gemma 3 27B4 cards$837.2410–15 tokens/s
Qwen3 32B4 cards$837.248.4–13 tokens/s
Llama 3.3 70B7 cards$1,6593.9–5.9 tokens/s
gpt-oss 120Bmore than 8——
Qwen3 235B-A22Bmore than 8——
DeepSeek R1 / V3 671Bmore 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 2060 8 GB neededCosts nowPer question (est.)
Julia-10.144B1 card$200.0021–46 ms
Laya0.421B1 card$200.0035–76 ms
Kev-4B4B1 card$200.0085–182 ms
lev4B1 card$200.00255–547 ms
OpenJev27B3 cards$612.27305–653 ms
Clef27B3 cards$612.27305–653 ms
Perplexity Decider v1.227B3 cards$612.27305–653 ms
mammoth-127B3 cards$612.27305–653 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 2060 8 GB. These open the shop's own search; we don't show their prices here.