EdgeAI.computer

Hardware

AI Workstations

Desktop and mobile machines for model development and local inference

AI workstations give engineering teams local capacity for data preparation, fine-tuning and running larger models without sending data to a shared cloud environment.

Solutions in this category

Representative platforms with the details engineering and procurement teams shortlist on.

Compact desktop AI machine on a dark workbench
AMD

AMD Ryzen AI Max+ 395

Sixteen-core Zen 5 processor with an XDNA 2 NPU rated above 50 TOPS and up to 128 GB of unified memory.

NPU
XDNA 2, more than 50 peak AI TOPS
CPU
16-core Zen 5, 32 threads, up to 5.1 GHz boost
GPU
RDNA 3.5, up to 40 compute units
Deployment
Mobile workstation, mini PC or compact desktop
Local large model inference
Creative and engineering workstations
On-premise prototyping
View DetailsCompareWebsite
Compact desktop AI supercomputer beside a monitor in a dim studio
NVIDIA

NVIDIA DGX Spark

Desktop AI system built on the GB10 Grace Blackwell Superchip with 128 GB of unified memory in a 150 mm chassis.

AI performance
Up to 1,000 TOPS inference, up to 1 PFLOP FP4 (sparse)
Processor
NVIDIA GB10 Grace Blackwell Superchip, 20-core Arm CPU (10× Cortex-X925, 10× Cortex-A725)
GPU
Blackwell GPU, 6,144 CUDA cores, 5th-gen Tensor cores
Deployment
Desk-side development environment or small on-premise lab
Local large model inference
Model fine-tuning
Robotics and vision development
View DetailsCompareWebsite
Professional AI workstation tower beside two monitors in a dim studio
Lenovo

Lenovo ThinkStation PX

Dual-socket workstation supporting up to 128 CPU cores and four NVIDIA RTX 6000 Ada GPUs for local model work.

CPU
Dual 5th Gen Intel Xeon Scalable, up to 128 cores in total
GPU
Up to 4× NVIDIA RTX 6000 Ada Generation
Expansion
Up to 9 PCIe slots
Deployment
Office, lab or on-premise engineering environment
Model fine-tuning
Local LLM inference
Dataset preparation and simulation
View DetailsCompareWebsite

Specifications are summarised from publicly published manufacturer material and are provided for orientation only. Always confirm current figures directly with the manufacturer before purchasing or designing in.

Companies working in this category

NVIDIA

Chip manufacturer

Develops the Jetson family of edge system-on-modules, the DGX Spark desktop AI system and the JetPack, TensorRT and DeepStream software stacks used for edge inference, robotics and vision AI.

Santa Clara, California, United States

View Company

AMD

Chip manufacturer

Produces Ryzen AI processors that combine Zen 5 CPU cores, RDNA 3.5 graphics and the XDNA 2 NPU, with large unified memory configurations used for local generative AI workloads.

Santa Clara, California, United States

View Company

Dell Technologies

Cloud & infrastructure provider

Supplies the PowerEdge XR range of short-depth, edge-focused servers for industrial automation, video analytics and inference at retail, telecom and factory sites.

Round Rock, Texas, United States

View Company

Lenovo

Hardware manufacturer

Manufactures ThinkEdge edge servers and ThinkStation workstations, including multi-GPU platforms for local model development and EPYC-based edge systems for distributed sites.

Beijing, China / Morrisville, United States

View Company

Supermicro

Cloud & infrastructure provider

Builds IoT SuperServer and edge box systems with Xeon Scalable processors and full-height PCIe expansion for accelerators, aimed at telecom, industrial and retail edge sites.

San Jose, California, United States

View Company

AI Workstations: common questions

How much memory do I need to run a large model locally?
Memory requirement scales with parameter count and quantisation. Confirm the memory footprint published for the exact model build you intend to run rather than relying on general guidance.