NVIDIA Google TPU

TPU v5 Lite Pod (4 cores)

A four-core v5 Lite pod scales throughput while maintaining the low-latency TPU experience.

Launch year
2024
Memory
128 GB HBM
Memory bandwidth
>900 GB/s
Peak FP16 / FP32
240 TFLOPS · 0 TFLOPS

Market snapshot

$2.04 /hr

Range $2.04 – $6.24

Catalog coverage

32 live offerings

Across 1 providers · 18 regions

  • TPU pod connectivity
  • Good for medium training
  • Auto-scaling support
TPU v5 Lite Pod (4 cores) render

Last refreshed Oct 20, 2025, 2:01 AM

Performance snapshot

Normalized versus NVIDIA A100 (=1.0). Values use public reference benchmarks for training and inference workloads.

  • TPU Throughput×0.70
  • Energy Efficiency×0.85
  • Latency×0.60

Provider availability

Price bands per provider pulled from the live catalog.

  • Google Cloud logoGoogle Cloud32 offers
    $2.04 – $6.24 /hr

Popular regions

  • us-west4-b2 offers
  • us-west4-a2 offers
  • us-east5-a2 offers
  • us-east5-c2 offers
  • us-east5-b2 offers
  • us-west1-c2 offers
  • us-central1-a2 offers
  • europe-west1-c2 offers

Weighted average price $4.15 /hr · median $4.80