COMPARE / A10 VS A10G

A10 vs A10G

Specs from the chip makers' datasheets; prices from the live Compute Cafe panel, refreshed hourly. Every rate is an on-demand published price with a source receipt.

CHEAPEST A10
$0.150/hr
SpotGPUs · median $1.56 · 11 providers
CHEAPEST A10G
$1.000/hr
Hugging Face · median $1.25 · 4 providers
CHEAPER RIGHT NOW
A10
live panel, 2026-09-27
A10A10G
MAKERNVIDIANVIDIA
ARCHITECTUREAmpereAmpere
LAUNCHED20212021
MEMORY24 GB GDDR624 GB GDDR6
MEMORY BANDWIDTH600 GB/s600 GB/s
TENSOR COMPUTE125 TFLOPS FP16 tensor dense (250 sparse)125 TFLOPS FP16 tensor dense (250 sparse)
POWER DRAW150 W150 W
INTERCONNECTPCIe 4.0 x16PCIe 4.0 x16

HOW TO CHOOSE

A10 vs A10G
Same silicon, AWS-specific SKU with vGPU licensing for G5 instances. Performance is equivalent.
Workload fit
A10: mid-size inference, virtual workstations. A10G: mid-size inference, graphics workstations.

A10 VS A10G - FAQ

Which is cheaper to rent, A10 or A10G?
By today's published on-demand rates: A10 starts at $0.150/GPU/hr (median $1.56, 11 providers) and A10G starts at $1.000/GPU/hr (median $1.25, 4 providers). The cheapest live listing is the A10 at SpotGPUs. Figures recompute from the panel on every refresh.
A10 or A10G - which should I rent?
A10: The A10 fills Ampere's single-slot inference slot: 24 GB, respectable FP16 throughput, 150 W. A10G: The A10G is the AWS-specific variant of the A10, deployed in G5 instances with vGPU support. The side-by-side spec table and live price rows above give the full picture.
Where can I rent A10 and A10G?
11 providers publish A10 rates and 4 publish A10G rates on Compute Cafe. Every row links to the provider's own published price - committed-use and reserved rates are excluded.

Full pricing: A10 · A10G · all comparisons