Do these 3 things before closing this tab:
1Scan for outdated or missing drivers - takes under a minute2Repair Windows errors before they cause bigger problems3Fix the driver behind crashes, sound loss and screen glitchesiTechGuides is reader-supported. When you buy through links on our site, we may earn an affiliate commission. As an Amazon Associate I earn from qualifying purchases. Learn more
Amazon Bedrock AgentCore Runtime Instances can run multiple agents on the same AWS-managed EC2 instance when they use the same capacity provider and runtimeSessionId. This lets them share the instance’s filesystem and GPU access. Use Instances for long-running, stateful, collaborative, or GPU-dependent workflows; lightweight API-driven agents that finish quickly are generally a better fit for the default microVM compute type. Persistent files survive an instance stop only when stored on configured persistent volumes, and deleting the session deletes those volumes.
How does GPU colocation work?
Colocation is based on session sharing, not simply choosing the same GPU family. Configure the runtimes to use the same capacity provider and invoke them with the same runtimeSessionId. AgentCore can then place those agents on the same EC2 instance. They share its filesystem and have access to its GPUs, so this arrangement is useful when agents need to work against common files or coordinate GPU-backed tasks.
Because the resources are shared, GPU access is not an exclusive reservation for each agent. Plan capacity and concurrency around the combined workload. AWS documents GPU use for model inference, 3D rendering, and media processing, and says AgentCore provisions GPU drivers so standard container images can be used without bundling drivers.
The Tool Desk
Outbyte PC Repair FREERepair Windows errors before they cause bigger problemsFix Now →Outbyte Driver Updater FREEFix the driver behind crashes, sound loss and screen glitchesFind Drivers →Which GPU instance families are supported?
AWS’s AgentCore Instances guide lists these GPU-oriented EC2 families and one Inferentia2 family:
#1 Best Overall
- [ Maximum AI Compute Power ] Dominate complex workloads with the ASUS ESC8000A-E13. This 4U rack server is a powerhouse engineered for mass-scale AI, machine learning, and deep training. Featuring support for dual AMD EPYC 9005/9004 processors and up to eight dual-slot GPUs, it delivers the raw computational muscle required to train LLMs and run complex simulations effortlessly. Accelerate your data science pipeline and transform raw data into actionable intelligence faster than ever.
- [ Advanced Thermal Efficiency ] High performance demands elite cooling. The ESC8000A-E13 features a cutting-edge aerodynamic design with independent CPU and GPU airflow tunnels. Equipped with redundant hot-swap fans and optimized for liquid cooling integrations, this 4U server ensures maximum uptime under heavy, sustained workloads. Keep your data center running cool, quiet, and highly efficient while preventing thermal throttling during mission-critical enterprise operations.
- [ Scale with Flexible Storage ] Future-proof your infrastructure with unmatched storage and expansion flexibility. This offers comprehensive front-panel drive bays supporting Gen5 NVMe, SAS, or SATA drives alongside multiple PCIe 5.0 slots. Designed as a high-density 4U server capable of housing eight dual-slot GPUs: NVD H200, RTX PRO 6000 Blackwell, RTX PRO 4500 Blackwell or AMD Instinct MI350P PCIe Card, each supporting up to 600 watts.
- [ Enterprise-Grade Reliability ] Minimize downtime and secure your ecosystem with server-grade redundancy. The ESC8000A-E13 is built for 24/7 continuous operation, boasting 2+2 redundant (3200W total) 80 PLUS Titanium power supplies and integrated ASUS ASMB11-iKVM for comprehensive out-of-band management. Ideal for cloud service providers, rendering farms, and large enterprise infrastructure, it combines robust physical hardware with smart remote monitoring to safeguard your digital assets.
- [Reliability Guaranteed] Shop with total peace of mind knowing that every new computer component we sell is backed by our EPC 3-year warranty. Whether you are investing in high-speed DDR5 RAM or a powerhouse GPU, we protect your build against defects and performance failures. We stand firmly behind the quality of our hardware, ensuring that your setup remains fast, stable, and secure for years to come.
- NVIDIA:
g4dn,g5,g6,g6e,gr6,g6f,gr6f, andg7e. - AWS Inferentia2:
inf2.
The list indicates supported families, not relative performance or availability in every AWS Region. Check the current Amazon Bedrock AgentCore Instances documentation for the target Region and workload before selecting a capacity provider. Compute/CUDA and graphics workloads are supported.
When should you use Instances instead of microVMs?
Instances and microVMs are designed for different workload shapes. Instances provide managed EC2 capacity in your AWS account; microVMs provide a serverless, consumption-based option suited to shorter-lived agents.
Rank #2
- NVIDIA Volta GV100 Architecture — 4,608 CUDA Cores, 640 1st-Gen Tensor Cores delivering 14 TFLOPS FP32 and 112 TFLOPS deep learning performance for AI training, inference, HPC, and scientific computing workloads
- 32GB HBM2 ECC Memory — 900 GB/s Bandwidth — High-bandwidth memory on a 4096-bit bus with ECC error correction provides the memory capacity and throughput required for the largest AI models, simulations, and datasets
- PCIe 3.0 x16 Interface — 250W TDP — Standard PCIe Gen3 connectivity with passive cooling designed for enterprise rack server deployment in HPE ProLiant, Dell PowerEdge, and Supermicro platforms with adequate chassis airflow
- NVLink — Scale to 96GB Unified Memory — Connect two V100 GPUs via NVLink at 300 GB/s bi-directional bandwidth to scale GPU memory from 32GB to 96GB for larger AI training and HPC workloads
- Multi-Precision Computing — Supports FP64 (7 TFLOPS), FP32 (14 TFLOPS), FP16 (112 TFLOPS) and INT8 precision modes for flexible deployment across training, inference, and scientific simulation workloads
| Consideration | Instances | microVMs |
|---|---|---|
| Typical fit | Long-running, stateful, collaborative, or GPU-based workloads | Lightweight, API-driven agents that complete quickly |
| Maximum documented session runtime | Up to 14 days | Up to 8 hours |
| GPU support | Supported families are selected through a capacity provider | Not supported |
| Agents per session | Multiple agents can share an instance when configured with the same capacity provider and session ID | One runtime hosts one agent |
| Infrastructure and billing model | EC2 managed in your AWS account; applicable EC2 pricing mechanisms may be used | AgentCore consumption-based, serverless model |
| Persistent filesystem | Capacity-provider EBS volumes can retain files until the session is deleted | Separate microVM storage options apply; check their current availability and lifecycle details |
The 14-day and 8-hour figures are documented maximum session runtimes, not a promise that an individual instance stays active for that entire period. Lifecycle settings govern idle timeout and maximum instance lifetime.
Crashes, No Sound, or Screen Glitches?
Random freezes, missing sound and display glitches usually trace back to one bad driver. Find and replace yours safely.Free scan · under a minuteWindows Errors? Fix Them Before They Spread
Repair common Windows errors and clear accumulated junk for a smoother, more stable PC - no reinstall needed.Free scan · no reinstallDoes AgentCore keep files when a session stops?
Only files placed on configured persistent EBS volumes are retained across an instance stop. A capacity provider can define these volumes; AgentCore creates them in your AWS account and mounts them into the agent. They can hold workspace files, caches, and checkpoints. Root and ephemeral volumes are temporary and do not provide this persistence.
Rank #3
- AI-Optimized: Designed to support up to 4 GPUs, it is perfect for handling intensive AI and machine learning tasks, ensuring high performance and scalability for advanced computational needs.
- Intelligent Storage: Equipped with 8 hot-swappable 3.5" SATA/SAS drives (12Gbps), featuring SGPIO and temperature control, it ensures efficient data management and reliable storage performance.
- Robust Cooling: The system includes 3x 12038 hot-swap PWM fans and 2x 8038 rear fans, providing advanced thermal management to maintain optimal temperatures and ensure stable operation under heavy workloads.
- Rack-Ready: Comes with a pre-installed rail kit, allowing for quick and easy installation in standard 19-inch server racks, making it ideal for data center environments and enterprise setups.
- Versatile Connectivity: Offers USB 3.0 and the latest USB 3.2 Type-C ports, ensuring high-speed data transfer and compatibility with a wide range of peripherals and devices for enhanced connectivity options.
Stopping an instance and deleting a session are different lifecycle events. Persistent volumes can remain available when compute stops, but deleting the session removes its persistent volumes too. Treat session deletion as a data-lifecycle action: copy anything you need to keep elsewhere before deleting the session.
A session is associated with a runtimeSessionId. Instances sessions can run for up to 14 days. When an instance reaches its configured lifetime and stops, invoking the session again with the same ID can provision replacement compute and reattach persistent storage. The documented upper bound for Instances maximum instance lifetime is 1,209,600 seconds (14 days); configure lifecycle settings to suit the workflow rather than assuming compute remains continuously running.
Rank #4
- Professional AI & Creator Workstation: AMD Radeon AI PRO R9700 GPU with 32GB GDDR6 is engineered for AI development, professional content creation, and compute-intensive workloads.
- Massive 32GB Memory Capacity: 32GB of GDDR6 memory on a 256-bit bus provides ample bandwidth for large AI models, 8K video editing, and complex 3D rendering.
- Advanced RDNA 4 with AI Accelerators: 64 Compute Units with 3rd Gen Ray Tracing and dedicated 2nd Gen AI Accelerators for groundbreaking AI performance and visual computing.
- Professional Blower Cooling: Efficient single blower design exhausts heat directly out of the chassis, ideal for multi-GPU workstation and server configurations.
- Enterprise-Grade Thermal Solution: Vapor chamber heatsink with industrial Honeywell PTM7950 thermal interface material ensures reliable cooling under sustained professional loads.
Is persistent workspace storage the same as AgentCore Memory?
No. EBS-backed capacity-provider volumes preserve workspace data such as files and checkpoints. AgentCore Memory is a separate capability for retaining selected conversational insights across sessions; it does not provide the same shared-filesystem semantics. AWS also documents customer-managed EFS or S3 Files mounts and microVM session storage as separate filesystem options, with different availability, sharing behavior, and VPC requirements. Review the current AgentCore Runtime filesystem configuration guide before choosing among them.
Where do infrastructure and costs sit?
With Instances, AgentCore provisions and operates EC2 managed instances inside your AWS account and handles lifecycle work such as patching, scaling, and teardown. You retain account-level controls and can use applicable EC2 pricing mechanisms. The actual cost depends on instance family, Region, storage, and runtime duration, so there is no useful generic price estimate without those inputs. Check regional availability and pricing for the intended configuration.
What to check before deploying a multi-agent workflow
- Select a capacity provider that supports the needed compute or GPU family in your target Region.
- Use the same capacity provider and
runtimeSessionIdfor agents intended to share an instance. - Decide which files must outlive an instance stop, and store them on configured persistent volumes rather than root or ephemeral storage.
- Set idle timeout and maximum instance lifetime with the workflow’s runtime and restart behavior in mind.
- Back up needed data before deleting a session, since session deletion removes its persistent volumes.
- Estimate costs using the chosen EC2 configuration, Region, storage, and expected run duration.
For the latest service behavior and supported families, consult AWS’s Instances guide, lifecycle settings documentation, and Runtime Instances data-management documentation.
Quick Recap
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
