Chip comparison
NVIDIA DRIVE Thor vs SambaNova SN40L
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 DRIVE Thor | SambaNova SN40L |
|---|---|---|
| Process node | TSMC 4NP | TSMC N5 |
| TDP | 130 W | 700 W |
| Memory | 128 GB LPDDR5X | 1500 GB DDR5 (three-tier: 64 MB SRAM + 64 GB HBM3 + 1.5 TB DDR5) |
| FP16 (dense) | — | 638 TFLOPS |
| FP8 (dense) | 2,000 TFLOPS | 1,250 TFLOPS |
| INT8 (dense) | 2,000 TOPS | — |
| Form factor | Auto-board | PCIe (SN40L DataScale system) |
| Announced | 2022-09-20 | 2023-09-19 |
| Released | 2025-06-01 | 2024-01-01 |
Robots running NVIDIA DRIVE Thor
Robots running SambaNova SN40L
No robots publicly running it yet.
Data centers with NVIDIA DRIVE Thor
No data centers publicly running it yet.
Data centers with SambaNova SN40L
No data centers publicly running it yet.
Common questions
NVIDIA DRIVE Thor vs SambaNova SN40L: which is faster for training?
NVIDIA DRIVE Thor has 1.60x the dense FP8 throughput of the other (NVIDIA DRIVE Thor: 2,000 TFLOPS; SambaNova SN40L: 1,250 TFLOPS). Real-world training speed also depends on memory bandwidth, interconnect, and software stack: see the spec diff for those inputs.
NVIDIA DRIVE Thor vs SambaNova SN40L: which has more memory?
SambaNova SN40L carries more HBM (NVIDIA DRIVE Thor: 128 GB LPDDR5X; SambaNova SN40L: 1500 GB DDR5 (three-tier: 64 MB SRAM + 64 GB HBM3 + 1.5 TB DDR5)). Memory capacity sets the largest model that fits on one chip without partitioning; memory bandwidth sets inference throughput.
NVIDIA DRIVE Thor vs SambaNova SN40L: which is more power-efficient?
Dense FP8 TFLOPS per watt: NVIDIA DRIVE Thor 15.38 (2,000 ÷ 130 W); SambaNova SN40L 1.79 (1,250 ÷ 700 W). NVIDIA DRIVE Thor wins at the die level; system-level efficiency also depends on cooling and interconnect.
NVIDIA DRIVE Thor vs SambaNova SN40L: which is more widely used?
NVIDIA DRIVE Thor: 11 robots and 0 data centers publicly running it. SambaNova SN40L: 0 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 DRIVE Thor full page · SambaNova SN40L full page.