A data center GPU against a workstation card, one Blackwell Ultra and one Blackwell: 288 GB HBM3e against 96 GB GDDR7, 5x the memory bandwidth on the B300, and NVLink 1,800 GB/s on the B300 where the RTX PRO 6000 is PCIe only.
At a glance
Memory
- B300
- 288 GB
- RTX PRO 6000
- 96 GB
3x more on B300
Memory bandwidth
- B300
- 8.00 TB/s
- RTX PRO 6000
- 1.60 TB/s
5x higher on B300
Cheapest on-demand
- B300
- $6.50 /GPU/hr
- RTX PRO 6000
- $0.66 /GPU/hr
9.8x more expensive on B300
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
| Billing | B300 | RTX PRO 6000 | Difference |
|---|---|---|---|
| On-demand | $7.87 /GPU/hr from $6.50 | $2.19 /GPU/hr from $0.66 | 3.6x more expensive on B300 |
| Reserved | $5.70 /GPU/hr from $4.25 | $1.79 /GPU/hr from $0.48 (1 mo) | 3.2x more expensive on B300 |
| Spot | $5.16 /GPU/hr from $4.30 | $1.19 /GPU/hr from $0.17 | 4.3x more expensive on B300 |
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. Verify before provisioning. More on how we price.
Price history
B300 vs RTX PRO 6000 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | B300 | RTX PRO 6000 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 288 GB HBM3e | 96 GB GDDR7 | 3x more on B300 |
| Bandwidth | 8,000 GB/s | 1,597 GB/s | 5x higher on B300 |
| Bus width | 8,192-bit | 512-bit | 16x wider on B300 |
| Compute · dense | |||
| FP4 | 14,000 TFLOPS | 2,000 TFLOPS | 7x higher on B300 |
| FP8 | 4,500 TFLOPS | 1,000 TFLOPS | 4.5x higher on B300 |
| FP16 / BF16 | 2,250 TFLOPS | 500 TFLOPS | 4.5x higher on B300 |
| INT8 | 153.5 TOPS | 1,000 TOPS | 6.5x higher on RTX PRO 6000 |
| FP32 | 75 TFLOPS | 120 TFLOPS | 1.6x higher on RTX PRO 6000 |
| FP64 | 1.2 TFLOPS | Not supported | B300 only |
| Platform | |||
| Interconnect | NVLink 1,800 GB/s | PCIe only | NVLink on B300 only |
| Board power | 1,100 W | 600 W | 1.8x higher on B300 |
| Released | Q1 2025 | Q1 2025 | |
| Precision | |||
| Supported formats | FP4FP6FP8FP16BF16TF32FP32FP64INT8 | FP4FP8FP16BF16TF32FP32INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: B300 datasheet and RTX PRO 6000 datasheet.
Where to rent them
Providers listing these GPUs, those with both first, so you can switch without moving clouds.
| Provider | B300 /GPU/hr | RTX PRO 6000 /GPU/hr |
|---|---|---|
Packet·ai
|
Custom on request | On-Demand $0.66 |
Runpod
|
On-Demand $7.89 | On-Demand $1.64 |
Lium
|
On-Demand $8.50 | On-Demand $1.19 |
GPU.ai
|
On-Demand $7.89 | -- |
EmpirioLabs AI
|
On-Demand $17.00 | -- |
TheAI Cloud
|
Reserved (24mo) $4.90 | -- |
Spheron
|
Spot $5.85 | -- |
GPUaaS
|
Custom on request | -- |
HyperAI
|
-- | On-Demand $0.80 |
Vast.ai
|
-- | On-Demand $1.00 |
GPUhub
|
-- | On-Demand $1.10 |
Verda
|
-- | On-Demand $1.84 |
UpCloud
|
-- | On-Demand $1.88 |
31 providers list the B300 and 47 the RTX PRO 6000. Every listing is on the B300 page and the RTX PRO 6000 page.
Similar GPUs
Other comparisons in the same class.
-
Nvidia H100
80 GB HBM3 · 58% less bandwidth than the B300
From $1.25 /GPU/hr Compare -
Nvidia B200
180 GB HBM3e · released Q1 2024
From $3.75 /GPU/hr Compare
-
Nvidia H200
141 GB HBM3e · 40% less bandwidth than the B300
From $2.09 /GPU/hr Compare
Our data for Nvidia B300 was last updated on Sept. 14, 2026, and for Nvidia RTX PRO 6000 on Sept. 14, 2026.