Nvidia A10G vs Nvidia Quadro RTX 6000

Both have 24 GB of memory. The Quadro RTX 6000 has 12% more bandwidth and is cheaper right now.

At a glance

Memory

Identical

A10G: 24 GB

Quadro RTX 6000: 24 GB

Memory bandwidth

12% higher on Quadro RTX 6000

A10G: 600 GB/s

Quadro RTX 6000: 672 GB/s

Cheapest on-demand

87% cheaper on Quadro RTX 6000

A10G: $1.00 /GPU/hr

Quadro RTX 6000: $0.13 /GPU/hr

Price comparison

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

Billing	A10G	Quadro RTX 6000	Difference
On-demand	-- /GPU/hr from $1.00	-- /GPU/hr from $0.13
Reserved	-- /GPU/hr from $0.43 (36 mo)	-- /GPU/hr from $0.12 (12 mo)

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 on-demand and reserved on the A10G and on-demand and reserved on the Quadro RTX 6000: 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

A10G vs Quadro RTX 6000 price history

Weekly median on-demand price per GPU per hour

Last 12 months

Aggregating historical prices...

Specs comparison

Spec	A10G	Quadro RTX 6000	Difference
Memory
Capacity	24 GB GDDR6	24 GB GDDR6	Identical
Bandwidth	600 GB/s	672 GB/s	12% higher on Quadro RTX 6000
Bus width		384-bit
Compute · dense
FP16 / BF16	70 TFLOPS	130.5 TFLOPS	86% higher on Quadro RTX 6000
INT8	140 TOPS	261 TOPS	86% higher on Quadro RTX 6000
FP32	35 TFLOPS	16.3 TFLOPS	2.1x higher on A10G
Platform
Interconnect	PCIe only	NVLink 100 GB/s	NVLink on Quadro RTX 6000 only
Board power	300 W	295 W	Within 5%
Released	Q2 2021	Q3 2018	3 years newer on A10G
Precision
Supported formats	FP16BF16TF32FP32INT4INT8	FP16FP32INT4INT8

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

Source: A10G datasheet and Quadro RTX 6000 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	A10G	Quadro RTX 6000
Hugging Face USA	$1.00 /GPU/hr On-demand	--
AWS USA	$1.01 /GPU/hr On-demand	--
Vast.ai USA	--	$0.13 /GPU/hr On-demand
Akamai Cloud USA	--	$1.50 /GPU/hr On-demand
Lambda Labs USA	--	$0.69 /GPU/hr On-demand