Nvidia B200 vs Nvidia RTX 4090

The B200 is newer, with 7.5x the memory and 7.6x the bandwidth. The RTX 4090 is typically cheaper.

At a glance

Memory

7.5x more on B200

B200: 180 GB

RTX 4090: 24 GB

Memory bandwidth

7.6x higher on B200

B200: 7.70 TB/s

RTX 4090: 1.01 TB/s

Cheapest on-demand

91% cheaper on RTX 4090

B200: $3.75 /GPU/hr

RTX 4090: $0.33 /GPU/hr

Price comparison

Median price per GPU per hour by billing type, with the cheapest listing under it.

Billing	B200	RTX 4090	Difference
On-demand	$6.64 /GPU/hr from $3.75	$0.48 /GPU/hr from $0.33	93% cheaper on RTX 4090
Reserved	$5.62 /GPU/hr from $3.75	$0.52 /GPU/hr from $0.29 (1 mo)	91% cheaper on RTX 4090
Spot	$4.26 /GPU/hr from $2.40	$0.33 /GPU/hr from $0.16	92% cheaper on RTX 4090

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

B200 vs RTX 4090 price history

Weekly median on-demand price per GPU per hour

Last 12 months

Aggregating historical prices...

Specs comparison

Spec	B200	RTX 4090	Difference
Memory
Capacity	180 GB HBM3e	24 GB GDDR6X	7.5x more on B200
Bandwidth	7,700 GB/s	1,010 GB/s	7.6x higher on B200
Bus width		384-bit
Compute · dense
FP4	9,000 TFLOPS	Not supported	B200 only
FP8	4,500 TFLOPS	330.3 TFLOPS	14x higher on B200
FP16 / BF16	2,250 TFLOPS	165.2 TFLOPS	14x higher on B200
INT8	4,500 TOPS	660.6 TOPS	6.8x higher on B200
FP32	75 TFLOPS	82.6 TFLOPS	10% higher on RTX 4090
FP64	37 TFLOPS	Not supported	B200 only
Platform
Interconnect	NVLink 1,800 GB/s	PCIe only	NVLink on B200 only
Board power	1,000 W	450 W	2.2x higher on B200
Released	Q1 2024	Q4 2022	17 months newer on B200
Precision
Supported formats	FP4FP6FP8FP16BF16TF32FP32FP64INT8	FP8FP16BF16TF32FP32INT4INT8

Compute: Vendor peak figures, dense and per GPU. Not measured throughput.

Source: B200 datasheet and RTX 4090 datasheet.

Where to rent them

Providers that rent these GPUs, with each one's cheapest rate. Providers that rent both are listed first.

Provider	B200	RTX 4090
Packet·ai USA	$3.75 /GPU/hr On-demand	$0.39 /GPU/hr On-demand
Vast.ai USA	$6.25 /GPU/hr On-demand	$0.34 /GPU/hr On-demand
Lium Distributed	$5.40 /GPU/hr On-demand SXM	$0.58 /GPU/hr On-demand
GPU.ai UAE	$6.79 /GPU/hr On-demand SXM	$0.34 /GPU/hr On-demand
Runpod USA	$6.79 /GPU/hr On-demand SXM	$0.34 /GPU/hr On-demand
Lyceum Germany	$6.49 /GPU/hr On-demand	--
Verda Finland	$6.99 /GPU/hr On-demand SXM	--
EmpirioLabs AI USA	$10.80 /GPU/hr On-demand	--
GPUhub Singapore	--	$0.44 /GPU/hr On-demand
Oblivus USA	--	$0.64 /GPU/hr On-demand PCIe
Sesterce France	--	$0.66 /GPU/hr On-demand