Flopper.io
Flopper.io GPU Specification Sheet

Huawei Ascend 960

Da Vinci v4 (chiplet) OAM 2027

Overview

—
FP32 TFLOPS
288 GB
Memory
9.6 TB/s
Memory Bandwidth
—
TDP

Performance Metrics

PrecisionPeak (dense)BitsType
FP64——Standard
FP32——Standard
TF32——Standard
BF161000.016Standard
FP161000.016Standard
FP82000.08Standard
FP6——Standard
FP44000.04Standard
INT8——Standard

Memory Specifications

Capacity
288 GB
Type
—
Bandwidth
9.6 TB/s
Interface Width
—

Power & Efficiency

TDP
—
Max power
—
FP32 dense TFLOPS per W of TDP
—
FP16 dense TFLOPS per W of TDP
—

Per W of TDP figures divide dense peak by accelerator TDP. Board power only: excludes host CPUs, networking, cooling and facility overhead.

Hardware Details

Vendor: Huawei
Architecture: Da Vinci v4 (chiplet)
Process Node: —
Form Factor: OAM
Launch Year: 2027

Interconnect

GPU-to-GPU: Unified Bus 2.0
Bandwidth: 2.2 TB/s direction and scope not stated by vendor