AI Compute

EQ Syntropy is optional and requires GPU-accelerated hardware. Every gateway runs EQ Coherence and EQ Sight without it. When you want Syntropy’s physics-informed analytics, event detection, and AI-assisted diagnostics, choose where to run it:

OptionHardwareData LocationBest For
Edge AI (Orin / Thor / DGX Spark)NVIDIA GPU on-siteLocal (NVMe SSD)Air-gapped sites, data sovereignty, lowest latency
EQ-HostedDedicated EQ serverReplicated to EQ serverNo GPU needed on-site; cross-site analytics
Customer-HostedCustomer data center GPU (RTX 4090 class or better)Customer serversEnterprise IT with existing GPU infrastructure

All options deliver the same Syntropy capabilities through EQ Sight. The choice depends on your network environment, data policies, and existing infrastructure.

With edge AI or customer-hosted deployments, AI inference runs entirely on local hardware. There are no per-query fees, no usage limits, and no dependency on external services.

EQ-hosted deployments provide the same Syntropy capabilities with EQ managing the AI infrastructure on your behalf.

Edge AI platforms

Three on-site GPU platforms, from hardened industrial edge to a high-capacity developer node:

PlatformTierAI PerformanceMemorySensor NetworkOperating TempForm Factor
AGX Orin (NRU-220S)Industrial edge275 INT8 TOPS64 GB LPDDR55 direct GbE PoE+ ports−25 to 50 °CFanless industrial
Thor (MIC-742-AT)Industrial edge (high density)2,070 FP4 TFLOPs128 GB LPDDR5XQSFP28 breakout to switches−10 to 60 °CIndustrial edge server
DGX SparkDeveloper / lab / eval~1 PFLOP (FP4)128 GB unified200GbE via switch~0–35 °C (office)Desktop (not industrial)
Standard GatewayNo AI (baseline)None (CPU only)4 GB1 dedicated port−40 to +80 °CDIN-rail gateway

Orin and Thor are hardened, always-on industrial edge units. DGX Spark is a developer/evaluation-class desktop (the AI-compute analogue of the Lab Gateway) — use it for prototyping, benchmarking, and high-capacity on-prem evaluation, not hardened field deployment.

Software stack

Edge AI deployments run the same EQ stack regardless of platform:

LayerComponentPurpose
OSJetPack (Jetson Orin/Thor) or DGX OS (DGX Spark), Ubuntu-basedNVIDIA-optimized Linux
RuntimeCUDA, TensorRTGPU acceleration framework
DataEQ CoherenceCollection, storage, REST API
AIEQ SyntropyPhysics-informed analytics
InterfaceEQ SightWeb-based visualization


© 2026 EQ Systems Inc. • [email protected] • (415) 562–5251 • Updated March 2026