The B100 is newer, with 96x the memory and 276x the bandwidth.
At a glance
Memory
96x more on B100
- B100
- 192 GB
- K620
- 2 GB
Memory bandwidth
276x higher on B100
- B100
- 8,000 GB/s
- K620
- 29 GB/s
Cheapest on-demand
- B100
- --
- K620
- --
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
Price history
B100 vs K620 price history
Weekly median on-demand price per GPU per hour
Aggregating historical prices...
Specs comparison
| Spec | B100 | K620 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 192 GB HBM3e | 2 GB DDR3 | 96x more on B100 |
| Bandwidth | 8,000 GB/s | 29 GB/s | 276x higher on B100 |
| Bus width | 128-bit | ||
| Compute · dense | |||
| FP4 | 7,000 TFLOPS | Not supported | B100 only |
| FP8 | 3,500 TFLOPS | Not supported | B100 only |
| FP16 / BF16 | 1,750 TFLOPS | Not supported | B100 only |
| INT8 | 3,500 TOPS | Not supported | B100 only |
| FP32 | 60 TFLOPS | 0.9 TFLOPS | 70x higher on B100 |
| FP64 | 30 TFLOPS | Not supported | B100 only |
| Platform | |||
| Interconnect | NVLink 1,800 GB/s | PCIe only | NVLink on B100 only |
| Released | Q4 2024 | Q3 2014 | 10 years newer on B100 |
| Precision | |||
| Supported formats | FP4FP6FP8FP16BF16TF32FP32FP64INT8 | FP32 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: B100 datasheet and K620 datasheet.
Similar GPUs
Other comparisons in the same class.
Our data for Nvidia B100 was last updated on Sept. 14, 2026, and for Nvidia K620 on Sept. 14, 2026.