PerGB

Intel Arc Pro B60 48 GB

Live eBay prices, cheapest first. The best one right now is $2,049 (new).

Other sizes: 24 GB

Specs

VRAM
48 GB GDDR6
Bandwidth
456 GB/s
FP32
12.3 TFLOPS
FP16
98 TFLOPS
Power
200 W
Connector
PCIe 5.0
Released
2025
Llama 3.1 8B at Q4 (est.)
33–56 tokens/s

48 GB version is a dual-GPU card.

Price right now

Live on eBay
Lowest now$2,049
Median ask$2,789
Per GB VRAM$42.69
vs launch price—
Live listings15

From the live listings below; shipping included.

Listings

Live on eBay
ListingConditionPriceChecked
New$2,049−27%free shipping
New$2,055−26%free shipping
New$2,055−26%free shipping
New$2,055−26%free shipping
Open box$2,590or best offer−7%free shipping
New$2,635−6%free shipping
Open box$2,789or best offerfree shipping
Open box$2,789or best offerfree shipping
Open box$2,789or best offerfree shipping
Open box$2,789or best offerfree shipping
Open box$2,789or best offerfree shipping
Open box$2,789or best offerfree shipping
Open box$2,789or best offerfree shipping
New$3,518+$58.08 shipping
New$4,288or 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)Arc Pro B60 48 GB neededCosts nowSpeed (est.)
Llama 3.1 8B1 card$2,04933–56 tokens/s
Qwen3 14B1 card$2,04918–30 tokens/s
gpt-oss 20B1 card$2,04944–75 tokens/s
Gemma 3 27B1 card$2,0499.6–16 tokens/s
Qwen3 32B1 card$2,0498.0–14 tokens/s
Llama 3.3 70B1 card$2,0493.7–6.4 tokens/s
gpt-oss 120B2 cards$4,10431–53 tokens/s
Qwen3 235B-A22B4 cards$8,2147.2–12 tokens/s
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)Arc Pro B60 48 GB neededCosts nowPer question (est.)
Julia-10.144B1 card$2,04912–27 ms
Laya0.421B1 card$2,04921–44 ms
Kev-4B4B1 card$2,04949–106 ms
lev4B1 card$2,049148–318 ms
OpenJev27B1 card$2,049177–380 ms
Clef27B1 card$2,049177–380 ms
Perplexity Decider v1.227B1 card$2,049177–380 ms
mammoth-127B1 card$2,049177–380 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 Intel Arc Pro B60 48 GB. These open the shop's own search; we don't show their prices here.