Intel Arc A750 - 8GB usable

8GB with solid bandwidth, and Intel's SYCL stack has matured. Still the least-travelled path in local AI: fewer answers when it breaks.

Specifications

BrandIntel
ModelArc A750
Usable VRAM8GB
ArchitectureXe-HPG
CUDA / Stream Processors3,584
Memory Bandwidth512 GB/s
TDP225W
FP32 TFLOPS17.2

Current Offers

Used from $150New from $210

Prices last updated:

GPUDojo is reader-supported. When you buy through links on our site, we may earn an affiliate commission.

Lowest tracked offers by retailer

US · USD · Weekly since May 2026 · Shipping may be extra

$100$150$200$250$300May 8Jun 21Aug 5Sep 19Nov 3Newegg $210Amazon $165eBay $150
About these prices

Each line is the lowest offer we tracked from that retailer at weekly snapshots, ending at today's offer. The condition can vary between snapshots (new, used, or unrecorded for older ones). eBay prices exclude shipping. Tax is excluded. Amazon shows a current price only.

Weekly offers table
Lowest tracked offer per retailer · US · USD
DateeBayAmazonNewegg
Today, Nov 3, 2026 $149.99$164.99$209.99
Oct 30, 2026 $149.99–$209.99
Oct 23, 2026 $169.00–$209.99
Oct 9, 2026 $149.99–$222.99
Oct 2, 2026 $164.99–$199.00
Sep 25, 2026 $164.99–$209.00
Sep 18, 2026 $179.00–$199.00
Sep 11, 2026 $179.95–$199.00
Sep 4, 2026 $170.00–$222.99
Sep 1, 2026 $170.00–$222.99
Aug 28, 2026 $170.00–$209.99
Aug 21, 2026 $170.00–$209.99
Aug 14, 2026 $176.72–$219.99
Aug 7, 2026 $179.50–$279.00
Jul 31, 2026 $164.99–$279.00
Jul 24, 2026 $179.00–$279.00
Jul 17, 2026 $190.00–$259.00
Jul 10, 2026 $179.00–$199.99
Jul 3, 2026 $160.00–$219.99
Jun 26, 2026 $157.00–$219.99
Jun 19, 2026 $149.00–$239.99
Jun 12, 2026 $159.99–$249.99
Jun 5, 2026 $140.00–$279.00
May 29, 2026 $159.99–$279.00
May 22, 2026 $145.97–$279.00
May 15, 2026 $159.99–$279.00
May 8, 2026 $159.99–$279.00

For AI / LLM Use

Limited VRAM restricts you to 7B quantized models. Expect a smaller selection of supported local-AI builds than on NVIDIA.

What Models Can It Run?

  • 7B Q6_K, 14B Q3_K (tight)
  • 7B Q4_K_M only

Estimated Performance

Generation: ~38 tokens/sec

Prefill: ~307 tokens/sec

Recommended Quantisations

  • Q4_K_M for 7B models
  • Q3_K for larger experiments

Pros & Cons

Pros

  • Consumer card: easy to install, display output

Cons

  • Only 8GB usable VRAM: limited to small models
  • Moderate memory bandwidth: not the fastest for inference
  • Smaller local-AI software ecosystem than NVIDIA or AMD

Community Verdict

No community reviews yet for the Arc A750. Know a good review? Let us know.