Intel Arc Pro A40 6GB vs Intel Arc A580 8GB
Side-by-side specifications, performance, and rental pricing for datacenter AI workloads.
Intel Arc Pro A40 6GB
Full specs →Intel Arc A580 8GB
Full specs →Specifications
Performance (TFLOPS)
FLOPS by Precision
What actually differs
The Arc A580 is the newer part: Alchemist, launched in 2023, against the Arc Pro A40's Alchemist from 2022. Newer architectures typically add lower-precision formats and better throughput per watt, so check the precision rows your workload actually uses.
Memory is 6 GB against 8 GB, fed at 192 GB/s versus 512 GB/s. More memory per GPU means larger models fit before you have to shard across cards, which often matters more than raw TFLOPS for inference.
For LLM training and inference, weight the FP8 and FP16 rows and memory capacity most heavily. For scientific and HPC workloads, the FP64 row is the one to read.
Frequently asked questions
Which has more memory, the Arc Pro A40 or the Arc A580?
The Arc A580 carries 8 GB of VRAM versus 6 GB for the Arc Pro A40. Memory bandwidth is 192 GB/s for the Arc Pro A40 and 512 GB/s for the Arc A580.
How much power do the Arc Pro A40 and the Arc A580 draw?
The Arc Pro A40 is rated at 50 W TDP and the Arc A580 at 185 W. On FP32 throughput per watt, the Arc Pro A40 is the more efficient part.
Get Comparison Updates
New GPUs added weekly. Be the first to see how they compare.