Huawei logo

Huawei Ascend 310 vs Huawei Atlas 300V Pro

The Atlas 300V Pro delivers 8.8x the FP16 throughput of the Ascend 310 (70 vs 8 TFLOPS dense).

Ascend 310: Da Vinci, 2018 Atlas 300V Pro: Da Vinci, 2022
FP16 dense lead
8.8x
Atlas 300V Pro: 70 vs 8 TFLOPS

Specifications

Huawei logo
Ascend 310
Huawei logo
Atlas 300V Pro
Architecture
Da VinciDa Vinci
Launch Year
20182022
Form Factor
SoCPCIe
Memory
—48 GB
Memory Bandwidth
—205 GB/s
TDP
8 W—
Process Node
12nm—

Performance (TFLOPS)

Huawei logo
Ascend 310
Huawei logo
Atlas 300V Pro
FP64
No verified data available No verified data available
FP32
No verified data available No verified data available
TF32
No verified data available No verified data available
BF16
No verified data available No verified data available
FP16
8 TFLOPS 70 TFLOPS
FP8
No verified data available No verified data available
FP6
No verified data available No verified data available
FP4
No verified data available No verified data available
INT8
16 TOPS 140 TOPS

FLOPS by Precision

What actually differs

The Atlas 300V Pro is the newer part: Da Vinci, launched in 2022, against the Ascend 310's Da Vinci from 2018. Newer architectures typically add lower-precision formats and better throughput per watt, so check the precision rows your workload actually uses.

Dense throughput for the Ascend 310 against the Atlas 300V Pro: FP16 8 vs 70 TFLOPS. Sparse figures, where the vendor publishes them, appear under each dense number in the performance table.

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 Ascend 310 faster than the Atlas 300V Pro?

At FP16 precision the Atlas 300V Pro reaches 70 TFLOPS dense against 8 TFLOPS for the Ascend 310. The performance table on this page lists every published precision for both GPUs.

Get Comparison Updates

New GPUs added weekly. Be the first to see how they compare.

© 2026 Flopper.io - Compare the hardware powering AI