The B100 is newer, with 32x the memory and 28x the bandwidth.
At a glance
Memory
32x more on B100
- B100
- 192 GB
- GTX 1660 Ti
- 6 GB
Memory bandwidth
28x higher on B100
- B100
- 8,000 GB/s
- GTX 1660 Ti
- 288 GB/s
Cheapest on-demand
- B100
- --
- GTX 1660 Ti
- --
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
Specs comparison
| Spec | B100 | GTX 1660 Ti | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 192 GB HBM3e | 6 GB GDDR6 | 32x more on B100 |
| Bandwidth | 8,000 GB/s | 288 GB/s | 28x higher on B100 |
| Bus width | 192-bit | ||
| Compute · dense | |||
| FP4 | 7,000 TFLOPS | Not supported | B100 only |
| FP8 | 3,500 TFLOPS | Not supported | B100 only |
| FP16 / BF16 | 1,750 TFLOPS | 10.9 TFLOPS | 161x higher on B100 |
| INT8 | 3,500 TOPS | Not supported | B100 only |
| FP32 | 60 TFLOPS | 5.4 TFLOPS | 11x 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 | Q1 2019 | 6 years newer on B100 |
| Precision | |||
| Supported formats | FP4FP6FP8FP16BF16TF32FP32FP64INT8 | FP16FP32 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: B100 datasheet and GTX 1660 Ti datasheet.
Similar GPUs
Other comparisons in the same class.
-
-
-
-
Nvidia RTX 3060
12 GB GDDR6 · 25% more bandwidth than the GTX 1660 Ti
On-demand from $0.08 /GPU/hr -
Nvidia RTX 2060
6 GB GDDR6 · 17% more bandwidth than the GTX 1660 Ti
On-demand from $0.06 /GPU/hr
Our data for Nvidia B100 was last updated on Sept. 14, 2026, and for Nvidia GTX 1660 Ti on Nov. 13, 2026.