dl2q.24xlarge vs dl1.24xlarge

Accelerators
Instance Type	dl2q.24xlarge	dl1.24xlarge
Instance Family	Machine Learning ASIC	Machine Learning ASIC
Details	Deep learning / Machine Learning (ML) inference and training dl – Deep Learning 2 – Generation q – Qualcomm inference accelerator 24xlarge – Size	Deep learning / Machine Learning (ML) inference and training dl – Deep Learning 1 – Generation 24xlarge – Size
vCPUs	96	96
Memory	768 GiB	768 GiB
CPU Architecture	n/a	x86_64
Processor	Intel Xeon Platinum 8259 (Cascade Lake)	Intel Xeon Platinum 8275L
Clock Speed		3 GHz
Threads Per Core	0	2
GPU	no	yes
GPU Name		Gaudi HL-205
GPU Manufacturer		Habana
GPUs	8
GPU Memory		32 GiB
GPU Total Memory		256 GiB
Inference Accelerator	no	no
Accelerator Memory	128 GiB
FPGA	no	no
Instances
Sizes	dl2q.24xlarge	dl1.24xlarge
Free Tier	no	no
Burstable	no	no
Hibernation	no	no
Instance Storage	EBS only	4 x 1000 GB NVMe SSD
EBS (Elastic Block Store)
EBS Optimized		default
Encryption		supported
NVMe		required
Dedicated Throughput	19000 MBps	19000 MBps
Optimized Baseline Bandwidth		19000 Mbps
Optimized Baseline Throughput		2375 Mbps
Optimized Baseline Performance		80000 IOPS
Optimized Max Performance		80000 IOPS
Optimized Max Bandwidth		19000 Mbps
Optimized Max Throughput		2375 Mbps
Networking
Networking Performance	100 Gigabit	400 Gigabit
Enhanced Networking	yes	no
Max Interfaces		60
Max Cards		4
IPv4 Addresses per Interface		50
IPv6 Addresses per Interface		50
IPv6 Support	no	yes
ENA Support		required
EFA Support	no	yes
EFA Max Interfaces		4
Encryption in Transit Support	no	yes
ENA SRD Support	no	no
Avg Price Diff	1.00x	1.28x

Regional Prices

Geography	Region	dl2q.24xlarge	dl1.24xlarge
Europe	Europe (Frankfurt) (eu-central-1)	11.5952	n/a
US	US East (Virginia) (us-east-1)	n/a	13.1090
US	US West (Oregon) (us-west-2)	8.9194	13.1090