Chip comparison
NVIDIA GB300 (Blackwell Ultra) 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 GB300 (Blackwell Ultra) | SambaNova SN40L |
|---|---|---|
| Process node | TSMC 4NP | TSMC N5 |
| TDP | 1400 W | 700 W |
| Memory | 288 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) | — | 638 TFLOPS |
| FP8 (dense) | 5,000 TFLOPS | 1,250 TFLOPS |
| Form factor | Superchip (Blackwell Ultra + Grace) | PCIe (SN40L DataScale system) |
| Announced | 2025-03-18 | 2023-09-19 |
| Released | 2025-11-01 | 2024-01-01 |
Robots running NVIDIA GB300 (Blackwell Ultra)
No robots publicly running it yet.
Robots running SambaNova SN40L
No robots publicly running it yet.
Data centers with NVIDIA GB300 (Blackwell Ultra)
Data centers with SambaNova SN40L
No data centers publicly running it yet.
Common questions
NVIDIA GB300 (Blackwell Ultra) vs SambaNova SN40L: which is faster for training?
NVIDIA GB300 (Blackwell Ultra) has 4.00x the dense FP8 throughput of the other (NVIDIA GB300 (Blackwell Ultra): 5,000 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 GB300 (Blackwell Ultra) vs SambaNova SN40L: which has more memory?
SambaNova SN40L carries more HBM (NVIDIA GB300 (Blackwell Ultra): 288 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 GB300 (Blackwell Ultra) vs SambaNova SN40L: which is more power-efficient?
Dense FP8 TFLOPS per watt: NVIDIA GB300 (Blackwell Ultra) 3.57 (5,000 ÷ 1400 W); SambaNova SN40L 1.79 (1,250 ÷ 700 W). NVIDIA GB300 (Blackwell Ultra) wins at the die level; system-level efficiency also depends on cooling and interconnect.
NVIDIA GB300 (Blackwell Ultra) vs SambaNova SN40L: which is more widely used?
NVIDIA GB300 (Blackwell Ultra): 0 robots and 1 data center 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 GB300 (Blackwell Ultra) full page · SambaNova SN40L full page.