AMD MI250
vs
Nvidia B300
The B300 is newer, with 2.2x the memory and 2.5x the bandwidth.
At a glance
Memory
2.2x more on B300
- MI250
- 128 GB
- B300
- 288 GB
Memory bandwidth
2.5x higher on B300
- MI250
- 3.20 TB/s
- B300
- 8.00 TB/s
Cheapest on-demand
MI250 is not sold on demand
- MI250
- --
- B300
- $4.99 /GPU/hr
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
| Billing | MI250 | B300 | Difference |
|---|---|---|---|
| On-demand | No on-demand listings | $9.15 /GPU/hr from $4.99 | |
| Reserved | -- /GPU/hr from $1.30 (12 mo) | $5.78 /GPU/hr from $4.25 | |
| Spot | No spot listings | $5.72 /GPU/hr from $4.08 |
Heads up: A provider's own page may quote a different figure, for example on tax, region or a promotion. A monthly-only plan shows a derived hourly rate. Medians are across providers, one vote each, so a large catalog does not outweigh a small one. No median for reserved on the MI250: we only show one when at least 3 providers list the GPU on that billing type. Verify before provisioning. More on how we price.
Price history
MI250 vs B300 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | MI250 | B300 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 128 GB HBM2e | 288 GB HBM3e | 2.2x more on B300 |
| Bandwidth | 3,200 GB/s | 8,000 GB/s | 2.5x higher on B300 |
| Bus width | 8,192-bit | 8,192-bit | Identical |
| Compute · dense | |||
| FP4 | Not supported | 14,000 TFLOPS | B300 only |
| FP8 | Not supported | 4,500 TFLOPS | B300 only |
| FP16 / BF16 | 362.1 TFLOPS | 2,250 TFLOPS | 6.2x higher on B300 |
| INT8 | 362.1 TOPS | 153.5 TOPS | 2.4x higher on MI250 |
| FP32 | 90.5 TFLOPS | 75 TFLOPS | 21% higher on MI250 |
| FP64 | 45.3 TFLOPS | 1.2 TFLOPS | 38x higher on MI250 |
| Platform | |||
| Interconnect | Infinity Fabric 400 GB/s | NVLink 1,800 GB/s | 4.5x higher on B300 |
| Board power | 500 W | 1,100 W | 2.2x higher on B300 |
| Released | Q4 2021 | Q1 2025 | 3 years newer on B300 |
| Precision | |||
| Supported formats | FP16BF16FP32FP64INT4INT8 | FP4FP6FP8FP16BF16TF32FP32FP64INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: MI250 datasheet and B300 datasheet.
Where to rent them
Providers that rent these GPUs, with each one's cheapest rate. No provider we track offers both right now.
| Provider | MI250 | B300 |
|---|---|---|
Cirrascale
USA
|
$1.30 /GPU/hr Reserved | -- |
Daytona
USA
|
-- | $7.10 /GPU/hr On-demand |
UpCloud
Finland
|
-- | $7.99 /GPU/hr On-demand SXM |
Lium
Distributed
|
-- | $8.00 /GPU/hr On-demand SXM |
Verda
Finland
|
-- | $10.48 /GPU/hr On-demand SXM |
Spheron
Singapore
|
-- | $12.41 /GPU/hr On-demand SXM |
Runcrate
USA
|
-- | $14.30 /GPU/hr On-demand NVL |
EmpirioLabs AI
USA
|
-- | $16.00 /GPU/hr On-demand |
GPUaaS
USA
|
-- | $5.00 /GPU/hr Custom SXM |
1 provider list the MI250 and 37 the B300. Every listing is on the MI250 page and the B300 page.
Similar GPUs
Other comparisons in the same class.
Our data for AMD MI250 was last updated on Sept. 14, 2026, and for Nvidia B300 on Sept. 14, 2026.