NVIDIA L4
The NVIDIA L4 is a Data Center graphics card based on the Ada Lovelace architecture. Released on 2023-03-21 with a launch price of $3,000.00, it features 7,424 CUDA cores and 24 GB of GDDR6 memory.
General info about L4
| Architecture | Ada Lovelace (AD104) |
| Market Segment | Data Center |
| Release Date | 2023-03-21 |
| Launch Price | $3,000.00 |
| Manufacturing Process | 4nm |
Technical specs of L4
| CUDA Cores | 7,424 |
| Base Clock Speed | 795 MHz |
| Boost Clock Speed | 2040 MHz |
| Transistor Count | 35.8B |
| VRAM Capacity | 24 GB GDDR6 |
| Memory Bus Width | 192 bits |
| Memory Bandwidth | 300.0 GB/s |
| TDP | 72 W |
Key Technical Parameters
Key technical parameters of the NVIDIA L4 include its 7,424 CUDA cores, 795 MHz base clock, and 2040 MHz boost clock, delivering high performance for data center applications.
Benchmark performance of L4
FP32 Performance
30
TFLOPS
FP16 Performance
120
TFLOPS
The NVIDIA L4 achieves 30 TFLOPS in FP32 performance, making it ideal for data center workloads.
Gaming performance of L4
Gaming Performance
The NVIDIA L4 is not designed for gaming. It is optimized for AI training, machine learning, and high-performance computing workloads.
Features and connectivity of L4
Tensor Cores
Gen 4
Transformer Engine
Disabled
Flash Attention
Not Supported
Connectivity
PCIe Gen4
Physical dimensions of L4
| Length | 6.1in |
| Width | 2.7in |
| Height | 1-slot |
Rankings and efficiency of L4
| Ranking Position | #10 |
| Popularity Ranking | #15 |
| Cost Effectiveness | 2.0/5 |
| Power Efficiency | 2.2/5 |
Cloud Availability
Available Instances
2
Starting Price
$0.43/hr
Top GPUs for Training and Inference
| Category | Rank 1 | Rank 2 | Rank 3 |
|---|---|---|---|
| Best for Training | NVIDIA H200 | NVIDIA H100 | NVIDIA B200 |
| Best for Inference | NVIDIA A40 | NVIDIA A100 | NVIDIA A10 |
Compare GPU specifications and cloud instances to find the best GPU for your workload.