NVIDIA T4 16GB
Performance
Peak theoretical throughput by precision type
| Precision | Peak |
|---|---|
FP64 | No verified data available |
FP32 32-bit floating point | 8.1TFLOPS |
TF32 | No verified data available |
BF16 | No verified data available |
FP16 16-bit floating point | 65TFLOPS |
FP8 | No verified data available |
FP6 | No verified data available |
FP4 | No verified data available |
INT8 8-bit integer | 130TOPS |
INT4 4-bit integer | 260TOPS |
Every figure here is dense. The vendor documents no structured (2:4) sparsity mode for this part, so there is no second number to quote.
Dense peak divided by accelerator TDP. Board power only: excludes host CPUs, networking, cooling and facility overhead. TDP for this part: 70 W.
The T4 16GB in the GPU landscape
Peak FP16 TFLOPS (dense) against TDP, single-GPU parts tracked by Flopper
Higher and further left is better: more half-precision throughput for less power.
Specifications
Architecture
Turing
Form Factor
PCIe
Launch Year
2019
Process Node
12nm
Memory
16 GB GDDR6
Bandwidth
300 GB/s
TDP
70 W
Max power (Flopper estimate)
~81 W est. Flopper estimate: 70 W TDP x 1.15. The vendor publishes no maximum board power for this part.
Spec Confidence
Official
Full Specifications
| Memory | |
|---|---|
| Memory | 16 GB |
| Memory Type | GDDR6 |
| Bandwidth | 300 GB/s |
| Interface Width | No verified data available |
| Power & Thermal | |
| TDP | 70 W |
| Max power (Flopper estimate) | ~81 W est. |
| Enterprise Features | |
| Sparsity | No |
| General | |
| Form Factor | PCIe |
| Architecture | Turing |
| Process Node | 12nm |
| Launch Year | 2019 |
Datasheet & Resources
Data Provenance
Every figure traced to a source
Primary Source
- Document
- —
- Publisher
- NVIDIA
- Published
- No verified data available
Data Quality
- Spec confidence
- Official
- Clock basis
- Boost
- Core precisions with figures
- 3 of 9
- Normalization
- All values in TFLOPS
Rent this GPU
$0.34 / GPU-hr
Lowest of 15 live listings across 6 providers· median $0.59
Median of each provider's cheapest on-demand listing, so a provider with many configurations counts once.
Price history and every provider on the pricing page. Some links are affiliate links.
Similar GPUs
Frequently Asked Questions
How many TFLOPS does the NVIDIA T4 have?
The NVIDIA T4 delivers 8.1 TFLOPS FP32 and 65 TFLOPS FP16 at peak. Flopper does not currently have a verified FP8 throughput figure for it.
What is the power consumption of the NVIDIA T4?
The NVIDIA T4 has a TDP (Thermal Design Power) rating of 70 watts.
How much memory does the NVIDIA T4 have?
The NVIDIA T4 is equipped with 16 GB of memory with 300 GB/s of memory bandwidth.
What architecture is the NVIDIA T4 based on?
The NVIDIA T4 is based on the Turing architecture, launched in 2019.
How much does the NVIDIA T4 cost to rent?
The NVIDIA T4 rents from $0.34 per GPU-hour across 6 cloud providers, the lowest of 15 live listings Flopper tracks. The pricing page lists every provider and the price history.
When did the NVIDIA T4 come out?
The NVIDIA T4 launched in 2019 on the Turing architecture.
Stay Updated on GPU Releases
Get notified when new GPUs are added or specifications are updated.
No spam, unsubscribe anytime.