PerGB

AMD Radeon RX 9070

Live eBay prices, cheapest first. The best one right now is $800.00 (open box).

Other sizes: 12 GB

Specs

VRAM
16 GB GDDR6
Bandwidth
640 GB/s
FP32
36.1 TFLOPS
FP16
145 TFLOPS
Power
220 W
Connector
PCIe 5.0
Released
2025
Launch price
$549.00
Llama 3.1 8B at Q4 (est.)
46–79 tokens/s

Price right now

Live on eBay
Lowest now$800.00
Median ask$914.99
Per GB VRAM$50.00
vs launch price46% over
Live listings32

From the live listings below; shipping included.

Listings

Live on eBay
ListingConditionPriceChecked
Open box$800.00−13%shipping not listed
Open box$815.00or best offer−11%shipping not listed
New$820.00−10%shipping not listed
Used$830.00−9%shipping not listed
Open box$840.00or best offer−8%shipping not listed
Used$848.99−7%free shipping
New$849.00−7%shipping not listed
New$849.99or best offer−7%shipping not listed
New$850.00−7%shipping not listed
Open box$850.00or best offer−7%shipping not listed
New$850.00or best offer−7%shipping not listed
Open box$875.00or best offershipping not listed
Open box$895.95or best offerfree shipping
New$900.00free shipping
Open box$900.00or best offershipping not listed
Refurbished$909.99free shipping
New$919.99free shipping
New$930.00or best offershipping not listed
New$978.99free shipping
New$999.99free shipping
New$1,018free shipping
New$1,259free shipping
New$1,266free shipping
New$1,269or best offerfree shipping
New$1,269or best offerfree shipping
New$1,299or best offerfree shipping
New$1,306free shipping
New$1,309free shipping
New$1,329or best offer+$29.90 shipping
New$1,350or best offerfree shipping
New$1,350or best offerfree shipping
New$1,396or 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

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)Radeon RX 9070 neededCosts nowSpeed (est.)
Llama 3.1 8B1 card$800.0046–79 tokens/s
Qwen3 14B1 card$800.0025–43 tokens/s
gpt-oss 20B1 card$800.0062–106 tokens/s
Gemma 3 27B2 cards$1,61513–23 tokens/s
Qwen3 32B2 cards$1,61511–19 tokens/s
Llama 3.3 70B4 cards$3,2655.2–9.0 tokens/s
gpt-oss 120B5 cards$4,10543–75 tokens/s
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)Radeon RX 9070 neededCosts nowPer question (est.)
Julia-10.144B1 card$800.008.6–18 ms
Laya0.421B1 card$800.0014–31 ms
Kev-4B4B1 card$800.0034–74 ms
lev4B1 card$800.00103–221 ms
OpenJev27B2 cards$1,615123–264 ms
Clef27B2 cards$1,615123–264 ms
Perplexity Decider v1.227B2 cards$1,615123–264 ms
mammoth-127B2 cards$1,615123–264 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 AMD Radeon RX 9070. These open the shop's own search; we don't show their prices here.