Intel Arc A580 - 8GB usable

The entry point to 8GB Arc, fine for 7B experiments. Slowest of the line on the least-supported stack: buy it to learn, not to rely on.

Specifications

BrandIntel
ModelArc A580
Usable VRAM8GB
ArchitectureXe-HPG
CUDA / Stream Processors3,072
Memory Bandwidth512 GB/s
TDP185W
FP32 TFLOPS10.4

Current Offers

Used from $215New from $165

Prices last updated:

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

Price History

  • eBay$215mid-range
  • Amazon$184current
  • Newegg$165at high
Aug 21Aug 28Sep 1Sep 4$140$165$215$215$184

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: ~186 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 A580. Know a good review? Let us know.