NVIDIA L4 24GB
Performance
Peak theoretical throughput by precision type
| Precision | Dense | 2:4 Sparse |
|---|---|---|
FP64 64-bit floating point | 0.4TFLOPS | Structured sparsity is a tensor-core feature; this vector precision has no sparse form |
FP32 32-bit floating point | 30TFLOPS | Structured sparsity is a tensor-core feature; this vector precision has no sparse form |
TF32 TensorFloat-32 | 60TFLOPS | 120TFLOPS |
BF16 Brain Float 16 | 121TFLOPS | 242TFLOPS |
FP16 16-bit floating point | 121TFLOPS | 242TFLOPS |
FP8 8-bit floating point | 243TFLOPS | 485TFLOPS |
FP6 | No verified data available | The part supports 2:4 sparsity, but the vendor publishes no sparse figure for this precision |
FP4 | No verified data available | The part supports 2:4 sparsity, but the vendor publishes no sparse figure for this precision |
INT8 8-bit integer | 243TOPS | 485TOPS |
Dense peak divided by accelerator TDP. Board power only: excludes host CPUs, networking, cooling and facility overhead. TDP for this part: 72 W.
The L4 24GB 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
Ada Lovelace
Form Factor
PCIe
Launch Year
2023
Process Node
4nm
Memory
24 GB
Bandwidth
300 GB/s
TDP
72 W
Max power (Flopper estimate)
~83 W est. Flopper estimate: 72 W TDP x 1.15. The vendor publishes no maximum board power for this part.
Spec Confidence
Official
Full Specifications
| Memory | |
|---|---|
| Memory | 24 GB |
| Memory Type | No verified data available |
| Bandwidth | 300 GB/s |
| Interface Width | No verified data available |
| Power & Thermal | |
| TDP | 72 W |
| Max power (Flopper estimate) | ~83 W est. |
| Enterprise Features | |
| Sparsity | Yes |
| General | |
| Form Factor | PCIe |
| Architecture | Ada Lovelace |
| Process Node | 4nm |
| Launch Year | 2023 |
Datasheet & Resources
Data Provenance
Every figure traced to a source
Primary Source
- Document
- NVIDIA L4 Tensor Core GPU
- Publisher
- NVIDIA
- Published
- 2023-03-21
Data Quality
- Spec confidence
- Official
- Clock basis
- Boost
- Core precisions with figures
- 7 of 9
- Normalization
- All values in TFLOPS
Rent this GPU
$0.36 / GPU-hr
Lowest of 18 live listings across 10 providers· median $0.80
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
Systems Using This GPU
Pre-configured systems featuring the NVIDIA L4
| System | GPU Count | Peak Performance | Total Power | |
|---|---|---|---|---|
Wiwynn ES100G2 ES · rack · | 2x L4 | No verified data available | No verified data available | View System |
Frequently Asked Questions
How many TFLOPS does the NVIDIA L4 have?
The NVIDIA L4 delivers 30 TFLOPS FP32, 121 TFLOPS FP16 and 243 TFLOPS FP8 at peak.
What is the power consumption of the NVIDIA L4?
The NVIDIA L4 has a TDP (Thermal Design Power) rating of 72 watts.
How much memory does the NVIDIA L4 have?
The NVIDIA L4 is equipped with 24 GB of memory with 300 GB/s of memory bandwidth.
What architecture is the NVIDIA L4 based on?
The NVIDIA L4 is based on the Ada Lovelace architecture, launched in 2023.
How much does the NVIDIA L4 cost to rent?
The NVIDIA L4 rents from $0.36 per GPU-hour across 10 cloud providers, the lowest of 18 live listings Flopper tracks. The pricing page lists every provider and the price history.
When did the NVIDIA L4 come out?
The NVIDIA L4 launched in 2023 on the Ada Lovelace architecture.
Stay Updated on GPU Releases
Get notified when new GPUs are added or specifications are updated.
No spam, unsubscribe anytime.