Intel Arc A770 16GB - 16GB usable

16GB at 560 GB/s, a lot of capacity for an entry card, and llama.cpp runs on it via Vulkan or SYCL. Suits tinkerers, not people in a hurry.

Specifications

BrandIntel
ModelArc A770 16GB
Usable VRAM16GB
ArchitectureXe-HPG
CUDA / Stream Processors4,096
Memory Bandwidth560 GB/s
TDP225W
FP32 TFLOPS19.7

Current Offers

Used from $330New from $1,069

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

$0$250$500$750$1,000$1,250May 8Jun 21Aug 5Sep 19Nov 3Amazon $1,069eBay $330Newegg $200
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 $329.99$1,069.46–
Oct 30, 2026 $300.00––
Oct 23, 2026 $349.00––
Oct 9, 2026 $309.99––
Oct 2, 2026 $325.00–$199.99
Sep 25, 2026 $265.00–$199.99
Sep 18, 2026 $300.00–$199.99
Sep 11, 2026 $300.00–$199.99
Sep 4, 2026 $300.00–$199.99
Sep 1, 2026 $300.00–$199.99
Aug 28, 2026 $300.00–$199.99
Aug 21, 2026 $275.00–$199.99
Aug 14, 2026 $299.99–$199.99
Aug 7, 2026 $295.00–$379.00
Jul 31, 2026 $250.00–$199.99
Jul 24, 2026 $299.99–$389.00
Jul 17, 2026 $329.99–$379.00
Jul 10, 2026 $299.00–$379.00
Jul 3, 2026 $239.99–$379.00
Jun 26, 2026 $295.00–$389.00
Jun 19, 2026 $325.00–$389.00
Jun 12, 2026 $329.00–$379.00
Jun 5, 2026 $269.99–$389.00
May 29, 2026 $339.99–$389.00
May 22, 2026 $320.00–$389.00
May 15, 2026 $319.99–$379.00
May 8, 2026 $280.00–$369.00

For AI / LLM Use

Good for 14B models. 30B requires aggressive quantization. Expect a smaller selection of supported local-AI builds than on NVIDIA.

What Models Can It Run?

  • 14B Q6_K, 30B Q3_K (tight)
  • 14B Q4_K_M, 7B full precision
  • 7B Q6_K, 14B Q3_K (tight)
  • 7B Q4_K_M only

Estimated Performance

Generation: ~42 tokens/sec

Prefill: ~352 tokens/sec

Recommended Quantisations

  • Q4_K_M for 14B models
  • Q6_K for 7B-8B models
  • Q8 for 7B if VRAM allows

Pros & Cons

Pros

  • Consumer card: easy to install, display output

Cons

  • 16GB usable VRAM: may need quantization for 30B+ 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 A770 16GB. Know a good review? Let us know.