Google TPU v4 32GB
Performance
Peak theoretical throughput by precision type
Specifications
Architecture
TPU
Launch Year
2020
Memory
32 GB HBM2
Bandwidth
1,200 GB/s
Spec Confidence
Official
Datasheet & Resources
Flopper Datasheet
Google TPU v4 32GB specifications, generated from our database. Printable.
Vendor product page
Google documentation for the TPU v4 32GB
Data Provenance
Every figure traced to a source
Primary Source
- Document
- --
- Publisher
- Published
- --
Data Quality
- Spec confidence
- Official
- Clock basis
- Boost
- Precisions tracked
- 2
- Normalization
- All values in TFLOPS
Compare cloud providers offering on-demand GPU instances for AI training, inference, and HPC workloads.
Browse GPU Cloud ProvidersSimilar GPUs
Systems Using This GPU
Pre-configured systems featuring the Google TPU v4
| System | GPU Count | Peak Performance | Total Power | |
|---|---|---|---|---|
Google TPU v4 Pod TPU · pod · 2020 | 4096x TPU v4 | 1126.40 PFLOPS | -- | View System |
Frequently Asked Questions
How many TFLOPS does the Google TPU v4 have?
The Google TPU v4 delivers N/A TFLOPS for FP32 operations, N/A TFLOPS for FP16, and N/A TFLOPS for FP8 precision.
What is the power consumption of the Google TPU v4?
The Google TPU v4 has a TDP (Thermal Design Power) rating of N/A watts.
How much memory does the Google TPU v4 have?
The Google TPU v4 is equipped with 32 GB of VRAM with 1200 GB/s memory bandwidth.
What architecture is the Google TPU v4 based on?
The Google TPU v4 is based on the TPU architecture, launched in 2020.
Stay Updated on GPU Releases
Get notified when new GPUs are added or specifications are updated.
No spam, unsubscribe anytime.