Chip comparison
NVIDIA B100 (Blackwell) 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 B100 (Blackwell) | SambaNova SN40L |
|---|---|---|
| Process node | TSMC 4NP | TSMC N5 |
| TDP | 700 W | 700 W |
| Memory | 192 GB HBM3e | 1500 GB DDR5 (three-tier: 64 MB SRAM + 64 GB HBM3 + 1.5 TB DDR5) |
| Memory bandwidth | 8,000 GB/s | — |
| FP16 (dense) | 1,750 TFLOPS | 638 TFLOPS |
| BF16 (dense) | 1,750 TFLOPS | — |
| FP8 (dense) | 3,500 TFLOPS | 1,250 TFLOPS |
| Form factor | SXM6 (700 W envelope) | PCIe (SN40L DataScale system) |
| Announced | 2024-03-18 | 2023-09-19 |
| Released | 2024-11-01 | 2024-01-01 |
Robots running NVIDIA B100 (Blackwell)
No robots publicly running it yet.
Robots running SambaNova SN40L
No robots publicly running it yet.
Data centers with NVIDIA B100 (Blackwell)
No data centers publicly running it yet.
Data centers with SambaNova SN40L
No data centers publicly running it yet.
Common questions
NVIDIA B100 (Blackwell) vs SambaNova SN40L: which is faster for training?
NVIDIA B100 (Blackwell) has 2.80x the dense FP8 throughput of the other (NVIDIA B100 (Blackwell): 3,500 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 B100 (Blackwell) vs SambaNova SN40L: which has more memory?
SambaNova SN40L carries more HBM (NVIDIA B100 (Blackwell): 192 GB HBM3e; 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 B100 (Blackwell) vs SambaNova SN40L: which is more power-efficient?
Dense FP8 TFLOPS per watt: NVIDIA B100 (Blackwell) 5.00 (3,500 ÷ 700 W); SambaNova SN40L 1.79 (1,250 ÷ 700 W). NVIDIA B100 (Blackwell) wins at the die level; system-level efficiency also depends on cooling and interconnect.
See also: every chip comparison · NVIDIA B100 (Blackwell) full page · SambaNova SN40L full page.