Intel Arc Pro A40 6GB vs Intel Arc A770 16GB
The Arc A770 delivers 3.9x the FP32 throughput of the Arc Pro A40 (20 vs 5 TFLOPS dense). The Arc A770 also carries 10 GB more memory (16 GB vs 6 GB).
Intel Arc Pro A40 6GB
Full specs →Intel Arc A770 16GB
Full specs →Specifications
Performance (TFLOPS)
FLOPS by Precision
What actually differs
Both GPUs launched in 2022: the Arc Pro A40 on Alchemist and the Arc A770 on Alchemist.
Dense throughput for the Arc Pro A40 against the Arc A770: FP32 5 vs 20 TFLOPS. Sparse figures, where the vendor publishes them, appear under each dense number in the performance table.
Memory is 6 GB against 16 GB, fed at 192 GB/s versus 560 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.
Power budgets are 50 W for the Arc Pro A40 and 225 W for the Arc A770. At FP32 that works out to 0.10 against 0.09 TFLOPS per watt.
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
Is the Arc Pro A40 faster than the Arc A770?
At FP32 precision the Arc A770 reaches 20 TFLOPS dense against 5 TFLOPS for the Arc Pro A40. The performance table on this page lists every published precision for both GPUs.
Which has more memory, the Arc Pro A40 or the Arc A770?
The Arc A770 carries 16 GB of VRAM versus 6 GB for the Arc Pro A40. Memory bandwidth is 192 GB/s for the Arc Pro A40 and 560 GB/s for the Arc A770.
How much power do the Arc Pro A40 and the Arc A770 draw?
The Arc Pro A40 is rated at 50 W TDP and the Arc A770 at 225 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.