TPU v4
google · tpu · 32 GB HBM · 175W TDP
VRAM
32 GB
BF16 TFLOPS
275
Bandwidth
1200 GB/s
From
$2.25/hr
Spec Sheet
Pricing by Provider
| Provider | On-Demand | Reserved | Spot | Badge |
|---|---|---|---|---|
| gcp | $3.22/hr | $2.25/hr | - | Cheapest |
Compatible Models (282)
Single GPU (176 models)
Multi-GPU (106 models)
Training Capabilities
Estimated GPU count for full fine-tuning (AdamW, BF16) and QLoRA
| Model Size | Full Fine-Tune | QLoRA |
|---|---|---|
| 7B model | 5 GPUs | 1 GPU |
| 13B model | 8 GPUs | 1 GPU |
| 70B model | 42 GPUs | 2 GPUs |
Energy Efficiency
Estimated tokens/second per Watt for popular models
Similar GPUs
| GPU | VRAM | BF16 TFLOPS | BW (GB/s) | From |
|---|---|---|---|---|
| TPU v6e (Trillium) | 32 GB | 460 | 1640 | $1.75/hr |
| TPU v5e | 16 GB | 200 | 820 | $0.85/hr |
| RTX 5090 | 32 GB | 210 | 1792 | $0.89/hr |
| V100 32GB | 32 GB | 28.3 | 900 | $0.19/hr |
| Instinct MI100 | 32 GB | 184.6 | 1229 | $0.40/hr |
Methodology Note
Performance estimates for the TPU v4are based on InferenceBench's roofline performance model with CUDA kernel-level optimization including FlashAttention v2 and PagedAttention. Memory calculations account for model weights (32 GB HBM available), KV-cache allocation, and activation memory. Throughput predictions use the TPU v4's rated 1200 GB/s memory bandwidth and 275 BF16 TFLOPS compute capacity as roofline ceilings, with empirical correction factors per GPU architecture (tpu). See our full methodology.
Frequently Asked Questions
How many AI models can run on TPU v4?
The TPU v4 can run 282 AI models from our database within a single node. Compatible models range across various parameter sizes depending on the quantization precision (BF16, FP8, INT4). Smaller models fit on a single GPU while larger models may require multi-GPU setups up to 4096x TPU v4.
What is the TPU v4 inference throughput?
The TPU v4 delivers 275 BF16 TFLOPS and 275 FP8 TFLOPS with 1200 GB/s memory bandwidth. Actual inference throughput (tokens/sec) depends on the model size, precision, and batch size. Use our calculator for model-specific throughput estimates.
How much does TPU v4 cost per hour?
The TPU v4 is available starting from $2.25/hour via gcp. Prices vary by provider and pricing tier (on-demand, reserved, spot). Compare pricing across all providers in the table above.