NVIDIA L40S 48GB
Performance
Peak theoretical throughput by precision type
| Precision | Dense | 2:4 Sparse |
|---|---|---|
FP64 64-bit floating point | 1.4TFLOPS | Structured sparsity is a tensor-core feature; this vector precision has no sparse form |
FP32 32-bit floating point | 92TFLOPS | Structured sparsity is a tensor-core feature; this vector precision has no sparse form |
TF32 TensorFloat-32 | 183TFLOPS | 366TFLOPS |
BF16 Brain Float 16 | 362TFLOPS | 733TFLOPS |
FP16 16-bit floating point | 362TFLOPS | 733TFLOPS |
FP8 8-bit floating point | 733TFLOPS | 1,466TFLOPS |
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 | 733TOPS | 1,466TOPS |
INT4 4-bit integer | 733TOPS | 1,466TOPS |
Dense peak divided by accelerator TDP. Board power only: excludes host CPUs, networking, cooling and facility overhead. TDP for this part: 350 W.
The L40S 48GB 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
48 GB
Bandwidth
864 GB/s
TDP
350 W
Max power (Flopper estimate)
~402 W est. Flopper estimate: 350 W TDP x 1.15. The vendor publishes no maximum board power for this part.
Spec Confidence
Official
Full Specifications
| Memory | |
|---|---|
| Memory | 48 GB |
| Memory Type | No verified data available |
| Bandwidth | 864 GB/s |
| Interface Width | No verified data available |
| Power & Thermal | |
| TDP | 350 W |
| Max power (Flopper estimate) | ~402 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 L40S GPU
- Publisher
- NVIDIA
- Published
- 2023-08-08
Data Quality
- Spec confidence
- Official
- Clock basis
- Boost
- Core precisions with figures
- 7 of 9
- Normalization
- All values in TFLOPS
Rent this GPU
$0.60 / GPU-hr
Lowest of 42 live listings across 24 providers· median $1.50
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 L40S
| System | GPU Count | Peak Performance | Total Power | |
|---|---|---|---|---|
Wiwynn ES200G2 ES · rack · | 2x L40S | No verified data available | No verified data available | View System |
Frequently Asked Questions
How many TFLOPS does the NVIDIA L40S have?
The NVIDIA L40S delivers 92 TFLOPS FP32, 362 TFLOPS FP16 and 733 TFLOPS FP8 at peak.
What is the power consumption of the NVIDIA L40S?
The NVIDIA L40S has a TDP (Thermal Design Power) rating of 350 watts.
How much memory does the NVIDIA L40S have?
The NVIDIA L40S is equipped with 48 GB of memory with 864 GB/s of memory bandwidth.
What architecture is the NVIDIA L40S based on?
The NVIDIA L40S is based on the Ada Lovelace architecture, launched in 2023.
Stay Updated on GPU Releases
Get notified when new GPUs are added or specifications are updated.
No spam, unsubscribe anytime.