Announced at Google Cloud Next on 22 April 2026 and not yet shipping. Google says both eighth-generation TPUs will be generally available later in 2026, and neither has appeared in Google Cloud TPU documentation or release notes yet, so every figure here comes from Google's announcement blogs rather than from a spec table for a running machine type. Widely repeated claims that this chip is built on TSMC 2nm and arrives in late 2027 are supply-chain reporting about mass production, not Google statements. Captive silicon: Google has never sold TPUs as hardware and no third party can resell or host them, so they cannot be bought, and Google Cloud will be the only place to rent one.

Google TPU 8t NEW

TPU 8 2026
VRAM
216 GB
HBM3e
Bandwidth
6.5 TB/s
memory
View Providers

Overview

Google's eighth-generation training TPU, announced at Google Cloud Next in April 2026. Google publishes a peak of 12.6 PFLOPS of FP4 per chip, with 216 GB of HBM3e at 6,528 GB/s and 128 MB of on-chip Vmem SRAM. Its scale is the notable part: 9,600 chips form a single superpod on a 3D torus with 47 petabits per second of non-blocking bisectional bandwidth, and Google's Virgo network can link over 134,000 of them. FP4 is the only precision Google states for this chip; no FP8, BF16 or INT8 figure is published, and none is inferred from earlier TPU generations. Google publishes no sparse figure for any TPU, so this is a dense rate.

Performance Metrics

Peak theoretical throughput by precision type

PrecisionBitsPeak TFLOPS
FP4 4 12600.0

Power Specifications

TDP

--

Max Power

--

Power Connector

PCIe Slot

Cooling

Air

Memory Specifications

Capacity

216 GB

Type

HBM3e

Bandwidth

6528 GB/s

Interface

--

Hardware & Design

Form Factor

--

Architecture

TPU 8

Process Node

--

Launch Year

2026

Variant

Standard

Market Segment

Professional

Documentation & Resources

Common Use Cases

General Compute AI/ML Workloads Data Processing

The Google TPU 8t is optimized for high-performance computing tasks with TPU 8 architecture delivering high TFLOPS of compute power.

Where to Rent

Compare cloud providers offering on-demand GPU instances for AI training, inference, and HPC workloads.

Browse GPU Cloud Providers

Similar GPUs

Systems Using This GPU

Pre-configured systems featuring the Google TPU 8t

SystemGPU CountPeak PerformanceTotal Power
Google TPU 8t Superpod
TPU · pod · 2026
9600x TPU 8t 120960.00 PFLOPS -- View System

Stay Updated on GPU Releases

Get notified when new GPUs are added or specifications are updated.

Loading verification...

No spam, unsubscribe anytime.

Back to GPUs