vt1.24xlarge vs dl2q.24xlarge

Accelerators
Instance Type	vt1.24xlarge	dl2q.24xlarge
Instance Family	Media Accelerator	Machine Learning ASIC
Details	Fast real-time video transcoding and cost-effective live video stream transcoding. vt – Video transcoding 1 – Generation 24xlarge – Size	Deep learning / Machine Learning (ML) inference and training dl – Deep Learning 2 – Generation q – Qualcomm inference accelerator 24xlarge – Size
vCPUs	96	96
Memory	192 GiB	768 GiB
CPU Architecture	x86_64	n/a
Processor	Intel Xeon Platinum 8259CL	Intel Xeon Platinum 8259 (Cascade Lake)
Clock Speed	2.5 GHz
Threads Per Core	2	0
GPU	no	no
GPUs		8
Inference Accelerator	no	no
Accelerator Memory		128 GiB
FPGA	no	no
Instances
Sizes	vt1.24xlarge, vt1.3xlarge, vt1.6xlarge	dl2q.24xlarge
Free Tier	no	no
Burstable	no	no
Hibernation	no	no
Instance Storage	EBS only	EBS only
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	25000 Megabit	100 Gigabit
Enhanced Networking	no	yes
Max Interfaces	15
Max Cards	1
IPv4 Addresses per Interface	50
IPv6 Addresses per Interface	50
IPv6 Support	yes	no
ENA Support	required
EFA Support	yes	no
EFA Max Interfaces	1
Encryption in Transit Support	yes	no
ENA SRD Support	no	no
Avg Price Diff	1.00x	1.80x

Regional Prices

Geography	Region	vt1.24xlarge	dl2q.24xlarge
Europe	Europe (Ireland) (eu-west-1)	5.8729	n/a
Europe	Europe (Frankfurt) (eu-central-1)	n/a	11.5952
Hidden	Hidden (hidden-1)	6.5459	n/a
US	US East (Virginia) (us-east-1)	5.2000	n/a
US	US West (Oregon) (us-west-2)	5.2000	8.9194