Chip comparison
NVIDIA L40S vs Tesla HW4 (FSD Computer 2)
Side-by-side specs
Straight from each vendor's datasheet. Winner in bold: higher throughput, memory, or transistor count; lower power draw or price. Sparse (2:4) throughput roughly doubles the FP8/INT8 numbers shown.
| Field | NVIDIA L40S | Tesla HW4 (FSD Computer 2) |
|---|---|---|
| Process node | TSMC 4N | Samsung 7LPP |
| Transistors (B) | 76.3 | — |
| TDP | 350 W | 90 W |
| Memory | 48 GB GDDR6 | 16 GB GDDR6 |
| Memory bandwidth | 864 GB/s | — |
| FP16 (dense) | 362 TFLOPS | — |
| BF16 (dense) | 362 TFLOPS | — |
| FP8 (dense) | 733 TFLOPS | — |
| INT8 (dense) | 733 TOPS | 300 TOPS |
| Form factor | PCIe | Auto-board (dual-SoC) |
| Announced | 2023-08-08 | 2023-01-01 |
| Released | — | 2023-02-01 |
Robots running NVIDIA L40S
No robots publicly running it yet.
Robots running Tesla HW4 (FSD Computer 2)
Data centers with NVIDIA L40S
No data centers publicly running it yet.
Data centers with Tesla HW4 (FSD Computer 2)
No data centers publicly running it yet.
Common questions
NVIDIA L40S vs Tesla HW4 (FSD Computer 2): which has more memory?
NVIDIA L40S carries more HBM (NVIDIA L40S: 48 GB GDDR6; Tesla HW4 (FSD Computer 2): 16 GB GDDR6). Memory capacity sets the largest model that fits on one chip without partitioning; memory bandwidth sets inference throughput.
NVIDIA L40S vs Tesla HW4 (FSD Computer 2): which is more widely used?
NVIDIA L40S: 0 robots and 0 data centers publicly running it. Tesla HW4 (FSD Computer 2): 3 robots and 0 data centers. Empty here means no operator has said publicly, not zero adoption in the market.
See also: every chip comparison · NVIDIA L40S full page · Tesla HW4 (FSD Computer 2) full page.