L40 GPU accelerator
NVIDIA
Catalog context
Within its series, the L40 GPU accelerator ranks first of 36 for FP32 throughput and 7th of 32 for memory capacity. Its 300 W TDP is above the 75 W PCIe slot-power ceiling. The source does not record generation, codename, process and transistors, or 7 further fields, for this variant.
| Launch date | October 13, 2022 |
|---|---|
| Series | Data Center |
| Generation | — |
| Codename | — |
| Form factor | datacenter |
| Architecture | Ada Lovelace |
| Process | — |
| Transistors | — |
| Die size | — |
| Shaders | 18,176 |
| TMUs | 568 |
| ROPs | 192 |
| SM count | 142 |
| Base clock | 735 MHz |
| Boost clock | 2,490 MHz |
| Memory clock | — |
| Memory | 48 GB |
| Memory type | GDDR6 |
| Bus width | 384 bit |
| Bandwidth | 864 GB/s |
| Pixel fill rate | — |
| Texture fill rate | — |
| FP32 | 90,520 GFLOPS |
| FP64 | 1,414 GFLOPS |
| TDP | 300 W |
| Bus interface | — |
| External power required | — |
| Launch MSRP | — |
Explore related indexes
Every GPU With 16GB+ VRAM · Every GPU With 8GB+ VRAM
Source: Wikipedia, revision 1369488585 · catalog loaded 2026-08-16